© 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. 7-RES-JB
    11. 13469
    Prev
    Next
    INDEX
    Explanations

    long-term perspectives or considerations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to long-term considerations or impacts

    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
     Cosponsors
    -0.97
    HOU
    -0.85
    ©¶æ¥µ
    -0.81
    hou
    -0.80
    rote
    -0.79
    chu
    -0.76
     Mansion
    -0.74
    girls
    -0.72
    imates
    -0.72
    chy
    -0.71
    POSITIVE LOGITS
     viability
    1.07
     stability
    0.92
     commitment
    0.89
     sustainability
    0.88
     unemployed
    0.86
     memory
    0.86
     usefulness
    0.84
     survival
    0.83
     significance
    0.82
     ramifications
    0.78
    Activations Density 0.032%

    No Known Activations