© 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. 10903
    Prev
    Next
    INDEX
    Explanations

    phrases related to earning or exchanging points

    oai_token-act-pair · gpt-3.5-turbo

    references to points and rewards in a gaming or points-based system

    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
    uthor
    -0.87
    yss
    -0.78
     delinqu
    -0.74
    ntil
    -0.71
    DAQ
    -0.70
    ÄŁ
    -0.68
     tandem
    -0.68
    LECT
    -0.67
    ccording
    -0.67
    anical
    -0.67
    POSITIVE LOGITS
    manship
    1.02
    points
    0.90
     points
    0.82
    pread
    0.79
    point
    0.79
    heet
    0.78
    ense
    0.78
    Points
    0.74
     Points
    0.70
    hift
    0.70
    Activations Density 0.024%

    No Known Activations