© 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. 3741
    Prev
    Next
    INDEX
    Explanations

    the word "Cape" along with associated locations or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Cape."

    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
    arial
    -0.82
    amine
    -0.73
    omen
    -0.72
    iances
    -0.72
    arily
    -0.69
    naires
    -0.69
    atically
    -0.67
    orno
    -0.66
    orically
    -0.65
    ONSORED
    -0.65
    POSITIVE LOGITS
    llan
    1.07
    lla
    1.02
     Cod
    0.96
     Canaveral
    0.94
     Cape
    0.92
     Coral
    0.88
     Coast
    0.86
    reon
    0.85
     Nam
    0.82
    ttes
    0.76
    Activations Density 0.011%

    No Known Activations