© 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. 21480
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical exertion or strenuous activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of community gatherings and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Based
    -0.85
    ï¸ı
    -0.84
    Additionally
    -0.83
     Millennials
    -0.81
    itivity
    -0.80
     GMOs
    -0.79
    oÄŁ
    -0.79
     empowerment
    -0.78
    itiz
    -0.77
    ãĤ¢ãĥ«
    -0.76
    POSITIVE LOGITS
    ,—
    1.49
     supper
    1.37
     scarcely
    1.20
    Pg
    1.14
    morrow
    1.12
     Madame
    1.10
     negro
    1.10
     dreadful
    1.09
     melancholy
    1.09
     doubtless
    1.08
    Activations Density 0.534%

    No Known Activations