© 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. 2433
    Prev
    Next
    INDEX
    Explanations

    instances of conditional statements starting with "Even if"

    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
     Flavoring
    -0.81
    press
    -0.78
    dayName
    -0.75
    oru
    -0.74
    Ò
    -0.69
    ands
    -0.69
    atin
    -0.68
    vantage
    -0.68
    cue
    -0.67
    edition
    -0.67
    POSITIVE LOGITS
     you
    0.89
     they
    0.86
     we
    0.80
     SOME
    0.78
    fy
    0.78
     it
    0.76
     technically
    0.76
     there
    0.75
     hindsight
    0.73
     someone
    0.72
    Activations Density 0.039%

    No Known Activations