© 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. 0-RES-JB
    11. 2885
    Prev
    Next
    INDEX
    Explanations

    proper names related to various fields like politics, sports, and business

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals named Gilbert and Brewer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Umb
    -0.85
     Lanc
    -0.82
     droid
    -0.79
    isec
    -0.79
     Sith
    -0.79
     Underworld
    -0.74
    keeping
    -0.71
     Scythe
    -0.70
     Sv
    -0.69
     lightsaber
    -0.67
    POSITIVE LOGITS
     Gilbert
    3.36
     Brewer
    2.16
     Chandler
    1.95
    Gil
    1.37
     Jarrett
    1.35
     Granger
    1.30
     Gilmore
    1.27
     Barber
    1.25
     Pryor
    1.16
     Hubbard
    1.13
    Activations Density 0.025%

    No Known Activations