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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 10636
    Prev
    Next
    INDEX
    Explanations

    names of specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mention of specific entities or brands related to marine life and conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nect
    -0.87
    ives
    -0.79
    ivity
    -0.79
    essed
    -0.74
    ivable
    -0.70
    ework
    -0.70
    matically
    -0.68
    IVES
    -0.68
    orate
    -0.68
    innie
    -0.67
    POSITIVE LOGITS
     Fey
    0.81
    rament
    0.77
    opsis
    0.76
     Dogs
    0.74
    qual
    0.73
    EStream
    0.72
     Fet
    0.70
     Baal
    0.69
     Diver
    0.69
    adish
    0.68
    Activations Density 0.060%

    No Known Activations