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. 13804
    Prev
    Next
    INDEX
    Explanations

    places or objects that are improvised or makeshift

    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
    339
    +0.16
    0.6%
    326
    +0.15
    0.6%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.15
    326
    +0.15
    0.11
    99
    +0.13
    0.07
    Negative Logits
    rooms
    -1.02
    iments
    -1.00
    sen
    -0.98
    abad
    -0.94
    uid
    -0.93
    ophers
    -0.91
    mes
    -0.91
    rollers
    -0.90
    ozo
    -0.90
    arching
    -0.89
    POSITIVE LOGITS
     hitch
    0.94
     consolation
    0.94
     ceasefire
    0.86
     fortune
    0.85
     beginnings
    0.83
     truce
    0.83
     makeshift
    0.82
     memorial
    0.81
     minded
    0.80
     bargaining
    0.78
    Activations Density 1.933%

    No Known Activations