Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar L0 E2E Recon
    5. 2-RES_SLEFR-AJT
    6. 5394
    Prev
    Next
    INDEX
    Explanations

    terms related to RESTful APIs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    538
    +0.05
    0.5%
    194
    +0.05
    0.5%
    646
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.05
    0.01
    185
    +0.05
    0.01
    228
    +0.04
    0.01
    Negative Logits
    pn
    -0.36
    arenthood
    -0.35
    gee
    -0.34
    rs
    -0.34
    annie
    -0.34
    fw
    -0.34
    chy
    -0.34
    ased
    -0.33
    pos
    -0.32
    venants
    -0.32
    POSITIVE LOGITS
    indal
    0.36
    entin
    0.35
     Quin
    0.34
     tremend
    0.33
    arily
    0.33
    sembly
    0.33
     HAL
    0.32
     spoiler
    0.31
     Jal
    0.31
    liner
    0.30
    Activations Density 0.001%

    No Known Activations