© 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. 8-RES-JB
    11. 196
    Prev
    Next
    INDEX
    Explanations

    phrases related to responses or reactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "response" and its variations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    cutting
    -0.75
    ramer
    -0.72
    rome
    -0.71
     Zot
    -0.68
     knots
    -0.66
    BALL
    -0.65
    teenth
    -0.63
    cin
    -0.62
    raf
    -0.62
    ffe
    -0.60
    POSITIVE LOGITS
     thereto
    0.94
     response
    0.87
    naires
    0.82
    ivated
    0.81
     responses
    0.81
     Response
    0.80
     elic
    0.77
    aries
    0.74
    ivation
    0.73
     fielded
    0.73
    Activations Density 0.048%

    No Known Activations