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 CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13829
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "solid," such as solid objects or materials

    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
    167
    +0.14
    0.5%
    178
    +0.14
    0.5%
    99
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.09
    99
    +0.14
    0.07
    365
    +0.14
    0.04
    Negative Logits
    llor
    -0.92
    ~~~~~~~~~~~~~~~~
    -0.87
    uberty
    -0.83
     Mania
    -0.82
    TIT
    -0.82
    BOOK
    -0.82
    Hop
    -0.81
     Dise
    -0.81
    HAHA
    -0.80
     Forever
    -0.79
    POSITIVE LOGITS
    ified
    2.02
    ifying
    1.82
    ifies
    1.66
    ification
    1.57
    GoldMagikarp
    1.42
    ifier
    1.39
    ifiers
    1.39
    ify
    1.34
    ifications
    1.30
    izations
    1.28
    Activations Density 1.323%

    No Known Activations