© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    mentions where two entities are compared or contrasted

    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
    ithing
    -0.78
    nell
    -0.67
    amaru
    -0.67
    ascript
    -0.67
    roxy
    -0.67
    ļéĨĴ
    -0.66
    ãĤ¸
    -0.65
    plete
    -0.64
    rompt
    -0.64
    Ô
    -0.63
    POSITIVE LOGITS
     owes
    0.96
     respective
    0.93
     latter
    0.90
     pair
    0.89
     opted
    0.89
     suffers
    0.89
     succumbed
    0.89
     chose
    0.88
     deserves
    0.86
     seemed
    0.86
    Activations Density 0.284%

    No Known Activations