© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 12872
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or entities, particularly focusing on the Twin Towers and Twin Peaks

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    326
    +0.20
    0.6%
    167
    +0.19
    0.6%
    288
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.20
    0.08
    288
    +0.19
    0.10
    99
    +0.17
    0.06
    Negative Logits
    ulative
    -1.07
    stract
    -1.06
    vernment
    -1.04
    ãģĵ
    -1.01
    ublic
    -1.00
    inventoryQuantity
    -0.97
    glomer
    -0.91
    LES
    -0.91
    ãĤĮ
    -0.87
     Chemistry
    -0.86
    POSITIVE LOGITS
    ieth
    1.49
    hower
    1.37
    eenth
    1.37
     Peaks
    1.30
    fall
    1.25
     towers
    1.25
     Towers
    1.24
    sonian
    1.17
    tower
    1.14
    elve
    1.11
    Activations Density 1.174%

    No Known Activations