© 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. 9-RES-JB
    11. 3782
    Prev
    Next
    INDEX
    Explanations

    causal relationships between various factors and outcomes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atography
    -0.71
     Technique
    -0.70
     Instruments
    -0.69
    fml
    -0.67
    ffff
    -0.66
    ppings
    -0.65
    iband
    -0.65
    DragonMagazine
    -0.65
    ography
    -0.64
    ools
    -0.64
    POSITIVE LOGITS
     declines
    0.99
     deaths
    0.96
     deterioration
    0.93
     exacerb
    0.93
     decreased
    0.92
     increased
    0.92
     accelerating
    0.91
     declining
    0.91
     instability
    0.91
     worsening
    0.89
    Activations Density 0.266%

    No Known Activations