© 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. 5183
    Prev
    Next
    INDEX
    Explanations

    words related to attention and specific actions or behaviors

    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
    ktop
    -0.67
    FTWARE
    -0.66
     Giuliani
    -0.65
     Cuomo
    -0.64
    EStream
    -0.62
    vous
    -0.60
     shorth
    -0.60
     Kafka
    -0.58
    theless
    -0.58
    cular
    -0.58
    POSITIVE LOGITS
    orneys
    1.45
    ractive
    1.43
    itudes
    1.36
    ention
    1.35
    itudinal
    1.32
    ributed
    1.31
    raction
    1.31
    itude
    1.30
    ributes
    1.30
    achment
    1.26
    Activations Density 0.029%

    No Known Activations