© 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. 11-RES-JB
    11. 7136
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or groups of items or people

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossession
    -0.84
    Url
    -0.75
    -+-+
    -0.72
    UNCH
    -0.71
    ategory
    -0.70
    vertisement
    -0.69
    âķIJâķIJ
    -0.66
    inator
    -0.66
    wark
    -0.66
    utenant
    -0.66
    POSITIVE LOGITS
    worldly
    1.27
     prominent
    1.06
     members
    0.99
     finalists
    0.97
     contenders
    0.96
     defendants
    0.95
     attendees
    0.95
     notable
    0.95
     participants
    0.92
     claimants
    0.90
    Activations Density 0.113%

    No Known Activations