© 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. 15316
    Prev
    Next
    INDEX
    Explanations

    names of football players

    oai_token-act-pair · gpt-3.5-turbo

    specific organizational labels or identifiers, particularly related to roles or positions

    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
    flies
    -1.01
    eering
    -0.84
    eer
    -0.83
    ãĥ¼ãĥ³
    -0.82
    ãĥĹ
    -0.77
    ãĥĥãĤ¯
    -0.73
    âķIJâķIJ
    -0.72
    ãĥ¼ãĥĨ
    -0.71
    =-=-=-=-
    -0.68
    itia
    -0.68
    POSITIVE LOGITS
    PF
    0.84
     linemen
    0.83
    IVER
    0.81
    anguage
    0.79
     wrinkles
    0.78
    ibrary
    0.75
    iamond
    0.74
     lineman
    0.72
    OVA
    0.72
    TO
    0.71
    Activations Density 0.013%

    No Known Activations