© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 7751
    Prev
    Next
    INDEX
    Explanations

    mentions of the football club "Villa" at different player-related activities or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Villa" and entities associated with it

    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
    ether
    -0.80
    ship
    -0.78
    rity
    -0.70
    pots
    -0.70
    ãģ¦
    -0.70
    omen
    -0.69
    nature
    -0.69
    nr
    -0.69
    eworthy
    -0.69
    é¾įåĸļ士
    -0.69
    POSITIVE LOGITS
    ivable
    0.77
    itton
    0.76
    adium
    0.74
     Villa
    0.71
     Hills
    0.70
     mosqu
    0.69
     Gardens
    0.69
     Grounds
    0.68
    ocally
    0.65
     aback
    0.64
    Activations Density 0.040%

    No Known Activations