© 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. 10-RES-JB
    11. 23323
    Prev
    Next
    INDEX
    Explanations

    words related to instructions or commands

    oai_token-act-pair · gpt-3.5-turbo

    reasons for fights and mentions of character names in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ),
    -0.61
     ));
    -0.54
    icably
    -0.50
     disg
    -0.50
    Ħ¢
    -0.50
     ).
    -0.49
    Article
    -0.48
    ());
    -0.48
    utm
    -0.48
    oubted
    -0.48
    POSITIVE LOGITS
    :
    2.00
    %:
    1.92
    ?:
    1.84
    !:
    1.82
    *:
    1.76
    ):
    1.70
    :"
    1.69
    ':
    1.68
    ]:
    1.66
    .:
    1.65
    Activations Density 0.510%

    No Known Activations