© 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. 15253
    Prev
    Next
    INDEX
    Explanations

    phrases related to round-trip times, scheduling, and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to round trips and time-related concepts

    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
    ibly
    -0.73
     Pepe
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
     Lerner
    -0.68
    uala
    -0.67
    utical
    -0.66
    parser
    -0.66
    ratom
    -0.65
    PsyNetMessage
    -0.65
     Clement
    -0.63
    POSITIVE LOGITS
    leck
    0.72
    Higher
    0.71
    illon
    0.71
    Congratulations
    0.70
    Winner
    0.67
    teenth
    0.66
    Camera
    0.64
    cible
    0.64
     scrimmage
    0.64
    roup
    0.64
    Activations Density 0.106%

    No Known Activations