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

    Neuronpedia

    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 Local
    5. 6-RES_SCL-AJT
    6. 5001
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical instructions or information, particularly focusing on a specific context or topic

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    218
    +0.10
    0.5%
    679
    +0.10
    0.5%
    515
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.20
    740
    +0.10
    0.11
    326
    +0.10
    0.18
    Negative Logits
     unification
    -0.69
    umn
    -0.66
    ãĥ©ãĥ³
    -0.63
    ipop
    -0.63
    mAh
    -0.62
     membr
    -0.62
     ILCS
    -0.62
     reserve
    -0.61
     surv
    -0.60
     Grind
    -0.59
    POSITIVE LOGITS
    roleum
    1.10
    ertodd
    0.96
    sburgh
    0.91
    ients
    0.82
    kun
    0.77
    ername
    0.76
    ledge
    0.75
    ricia
    0.74
    itives
    0.74
    ersen
    0.74
    Activations Density 5.875%

    No Known Activations