© 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. 5026
    Prev
    Next
    INDEX
    Explanations

    words related to observations or statements about situations

    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
    ests
    -0.84
    ilts
    -0.79
    umbn
    -0.79
    izons
    -0.73
    andise
    -0.73
    orem
    -0.72
    otos
    -0.70
    oway
    -0.67
    perature
    -0.67
    ombs
    -0.65
    POSITIVE LOGITS
     unlikely
    0.94
     doubtful
    0.92
     probable
    0.83
     odd
    0.82
     plausible
    0.79
     ironic
    0.79
     impossible
    0.78
     inevitable
    0.78
     imperative
    0.77
     conceivable
    0.77
    Activations Density 0.050%

    No Known Activations