© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4081
    Prev
    Next
    INDEX
    Explanations

    conditional statements proposing potential solutions or improvements

    oai_token-act-pair · gpt-3.5-turbo

    statements about potential solutions or improvements to complex issues

    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
    emo
    -0.75
    aurus
    -0.75
     accuse
    -0.73
     grievance
    -0.73
    iverpool
    -0.70
    ãĥ³
    -0.70
    interstitial
    -0.67
    اØ
    -0.66
    agues
    -0.66
     accuses
    -0.65
    POSITIVE LOGITS
     careful
    0.87
     combining
    0.83
     supplementation
    0.77
     diligent
    0.77
     relying
    0.73
    standing
    0.70
     uninterrupted
    0.70
    cffff
    0.70
    achev
    0.69
     concerted
    0.69
    Activations Density 0.539%

    No Known Activations