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. 7-RES-JB
    6. 442
    Prev
    Next
    INDEX
    Explanations

    descriptions of strong, significant, or noticeable quantities or impacts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "overwhelming."

    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
    rint
    -0.82
    cius
    -0.77
    aunder
    -0.75
    ecast
    -0.74
    hops
    -0.70
    chery
    -0.69
    eport
    -0.68
    ials
    -0.68
    vern
    -0.67
    reenshots
    -0.67
    POSITIVE LOGITS
    whelming
    0.83
     majority
    0.82
     overwhelming
    0.82
     negativity
    0.78
     unbeliev
    0.74
     odds
    0.73
     reliance
    0.73
     obstacle
    0.71
     emotion
    0.70
    ingly
    0.70
    Activations Density 0.036%

    No Known Activations