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. 8-RES-JB
    6. 2896
    Prev
    Next
    INDEX
    Explanations

    mentions of current events and people

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and formatting symbols indicative of written text structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     boobs
    -0.79
     womb
    -0.78
     girls
    -0.77
     breasts
    -0.75
     sisters
    -0.75
     females
    -0.75
     moms
    -0.75
    redients
    -0.74
     Sisters
    -0.74
     panties
    -0.74
    POSITIVE LOGITS
    HAEL
    0.99
     Rodrigo
    0.95
     Mr
    0.93
     businessman
    0.90
    Mr
    0.90
    uterte
    0.89
     Theodore
    0.88
     preacher
    0.87
     rapper
    0.86
    Roger
    0.84
    Activations Density 0.711%

    No Known Activations