© 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. 7-RES-JB
    11. 24480
    Prev
    Next
    INDEX
    Explanations

    phrases related to identifying and solving problems or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to problem-solving or resolutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eligible
    -0.58
     Origin
    -0.57
     coordinates
    -0.56
     Scouting
    -0.56
    iew
    -0.54
    yip
    -0.54
     inclination
    -0.53
     surplus
    -0.53
    OPLE
    -0.53
    umbn
    -0.52
    POSITIVE LOGITS
     by
    1.04
     BY
    0.85
     anew
    0.78
    By
    0.78
    ĸļ
    0.75
     By
    0.75
     elsewhere
    0.73
     via
    0.72
     awa
    0.72
     accordingly
    0.71
    Activations Density 0.292%

    No Known Activations