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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 4202
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilo
    -0.72
    Kings
    -0.72
    Stars
    -0.71
    agraph
    -0.69
    kind
    -0.68
    leigh
    -0.67
    notations
    -0.62
    soType
    -0.61
    utical
    -0.61
    milo
    -0.61
    POSITIVE LOGITS
    ioned
    0.74
    IBLE
    0.71
     to
    0.69
    ible
    0.68
     for
    0.67
     punishable
    0.65
     prey
    0.65
    enged
    0.64
     tempting
    0.64
     elector
    0.62
    Activations Density 0.082%

    No Known Activations