© 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. 17976
    Prev
    Next
    INDEX
    Explanations

    restrictions or permissions related to the use of published, broadcasted, rewritten, or redistributed material

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to content publication rights and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Chern
    -0.63
     Galile
    -0.60
     shadow
    -0.60
     tal
    -0.57
    ties
    -0.57
    classified
    -0.56
     haunt
    -0.56
    gone
    -0.56
     appointed
    -0.54
    module
    -0.53
    POSITIVE LOGITS
    arnaev
    0.83
    nor
    0.78
    ãĤ¢ãĥ«
    0.69
    ãĤ´
    0.68
    owship
    0.66
    onga
    0.66
     liber
    0.65
    arbon
    0.65
     ILCS
    0.65
    âĢ¦)
    0.64
    Activations Density 0.029%

    No Known Activations