© 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. 2449
    Prev
    Next
    INDEX
    Explanations

    instances where the text mentions shifting attention or efforts towards a specific topic

    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
     signed
    -0.74
     photoc
    -0.70
    latable
    -0.69
    signed
    -0.69
     fluent
    -0.69
     Signed
    -0.67
     sued
    -0.64
     Amen
    -0.64
     convertible
    -0.61
     defied
    -0.61
    POSITIVE LOGITS
    phasis
    1.01
     squarely
    1.01
     toward
    0.92
     towards
    0.91
     emphasis
    0.89
     Towards
    0.89
    ocus
    0.85
    focus
    0.84
    vre
    0.83
     foc
    0.83
    Activations Density 0.310%

    No Known Activations