© 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. 2-RES-JB
    11. 994
    Prev
    Next
    INDEX
    Explanations

    the word "uses" in various contexts

    oai_token-act-pair · gpt-4-turbo

    instructions or steps using action verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "uses" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hai
    -0.63
    brother
    -0.63
     Patri
    -0.63
    naire
    -0.61
     Ou
    -0.61
    owship
    -0.61
     behold
    -0.60
    selves
    -0.60
     Hurricanes
    -0.59
    gee
    -0.59
    POSITIVE LOGITS
    paces
    0.97
    ettings
    0.95
    poons
    0.84
    uristic
    0.82
    fully
    0.82
    hops
    0.80
    uits
    0.78
     shortcuts
    0.77
    FUL
    0.76
    uggest
    0.75
    Activations Density 0.014%

    No Known Activations