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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5965
    Prev
    Next
    INDEX
    Explanations

    names of locations and titles with a focus on criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and significant entities within the text

    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
    •Partition Features Layer 8 GPT2 Small
    " token" vs "token"
    •Induction Feature

    No Comments

    Negative Logits
     ALS
    -0.88
     Unch
    -0.88
     acknow
    -0.88
     Pes
    -0.84
     IB
    -0.79
     MIS
    -0.79
     IPM
    -0.78
     estab
    -0.78
     thous
    -0.76
     Antar
    -0.75
    POSITIVE LOGITS
    shop
    1.39
    organ
    1.39
    run
    1.39
    floor
    1.38
    part
    1.37
    move
    1.37
    do
    1.36
    free
    1.35
    max
    1.34
    mist
    1.33
    Activations Density 0.389%

    No Known Activations