© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3068
    Prev
    Next
    INDEX
    Explanations

    phrases related to demanding or physically challenging tasks

    oai_token-act-pair · gpt-3.5-turbo
    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
    ulet
    -0.77
    idences
    -0.76
    idas
    -0.73
    isphere
    -0.72
    FLAG
    -0.72
    positive
    -0.71
    onyms
    -0.70
    ammad
    -0.67
    emn
    -0.67
     Shine
    -0.66
    POSITIVE LOGITS
     tedious
    0.98
     ardu
    0.97
     grind
    0.96
     slog
    0.96
     task
    0.94
     painstaking
    0.94
     tasks
    0.89
     ted
    0.86
    staking
    0.84
    intensive
    0.84
    Activations Density 0.181%

    No Known Activations