© 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. 0-RES-JB
    11. 8137
    Prev
    Next
    INDEX
    Explanations

    responses or reactions related to law enforcement, intelligence, or political issues

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "respond" or its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forged
    -0.74
     rumors
    -0.73
     rumor
    -0.73
     inflation
    -0.71
     Xuan
    -0.71
     algebra
    -0.69
    gang
    -0.69
     occult
    -0.68
     etched
    -0.68
    ãĤ´
    -0.68
    POSITIVE LOGITS
    Resp
    3.74
     Respons
    3.10
     Resp
    2.42
     Respond
    2.30
    respons
    2.13
     RESP
    2.11
     respons
    1.90
    respond
    1.76
    resp
    1.76
     Response
    1.65
    Activations Density 0.021%

    No Known Activations