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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 18608
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events being done or occurring

    oai_token-act-pair · gpt-3.5-turbo

    past participle verbs and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adra
    -0.94
    adan
    -0.80
    matically
    -0.70
    efully
    -0.70
    ively
    -0.66
    ptive
    -0.65
    hang
    -0.63
    pered
    -0.63
    strength
    -0.63
    doi
    -0.61
    POSITIVE LOGITS
    nesday
    1.03
    escription
    0.97
     Ones
    0.89
    irect
    0.88
    dit
    0.85
    paren
    0.82
    irection
    0.82
    monton
    0.82
    own
    0.81
    ragon
    0.80
    Activations Density 0.145%

    No Known Activations