© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 1815
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and application architecture, particularly focusing on technical details and coding practices

    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
    496
    +0.18
    0.6%
    623
    +0.17
    0.6%
    218
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.18
    0.04
    575
    +0.17
    0.04
    496
    +0.17
    0.04
    Negative Logits
    ²¾
    -0.99
    ord
    -0.96
    rolet
    -0.96
    etsk
    -0.92
    apes
    -0.91
    ricular
    -0.91
    haul
    -0.89
    inki
    -0.87
    hov
    -0.84
    primary
    -0.84
    POSITIVE LOGITS
    earance
    1.14
    mable
    1.07
    Crash
    1.04
    rehens
    1.02
    eering
    0.97
    matically
    0.97
     applications
    0.92
    ele
    0.91
    eals
    0.91
    lied
    0.91
    Activations Density 0.414%

    No Known Activations