© 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. 3-RES-JB
    11. 15106
    Prev
    Next
    INDEX
    Explanations

    locations, specifically county names

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and names associated with specific places or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izards
    -0.82
    ained
    -0.74
    andestine
    -0.74
    igion
    -0.71
    idential
    -0.71
    icone
    -0.70
    aining
    -0.68
    ractive
    -0.67
    atican
    -0.67
    artney
    -0.66
    POSITIVE LOGITS
    nect
    1.00
    keye
    0.92
    alez
    0.84
     cider
    0.83
     Fulton
    0.82
    hower
    0.81
    keyes
    0.79
    onne
    0.78
    otin
    0.76
    éĹĺ
    0.74
    Activations Density 0.016%

    No Known Activations