© 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. 4-RES-JB
    11. 14696
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations with a focus on bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and points of entry

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

    No Comments

    Negative Logits
    otos
    -0.73
    nel
    -0.71
    BUG
    -0.70
     subscriptions
    -0.69
    iple
    -0.69
    acci
    -0.68
    RY
    -0.67
    urrent
    -0.66
    attribute
    -0.64
     allocations
    -0.63
    POSITIVE LOGITS
    chool
    1.05
    cape
    0.94
    creen
    0.90
    erver
    0.87
    pace
    0.86
    pring
    0.86
    mith
    0.85
    paces
    0.83
     shores
    0.82
    gypt
    0.82
    Activations Density 0.019%

    No Known Activations