© 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. 14387
    Prev
    Next
    INDEX
    Explanations

    locations where conferences are held

    oai_token-act-pair · gpt-3.5-turbo

    references to conferences or events

    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
    Current
    -0.70
    ¶æ
    -0.70
    gans
    -0.68
    umatic
    -0.68
    esian
    -0.68
    Choice
    -0.67
     %%
    -0.64
    CLASSIFIED
    -0.64
     proble
    -0.62
    Amount
    -0.62
    POSITIVE LOGITS
     Cannes
    1.24
     Pasadena
    1.15
     Nashville
    1.12
     Louisville
    1.12
     Atlanta
    1.11
     Charlottesville
    1.11
     Hamburg
    1.11
     Minneapolis
    1.09
     Cologne
    1.08
     Philadelphia
    1.08
    Activations Density 0.191%

    No Known Activations