© 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. 1-RES-JB
    11. 16378
    Prev
    Next
    INDEX
    Explanations

    IP addresses related to a specific subnet

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with various entities or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olf
    -0.87
    matic
    -0.82
    agged
    -0.80
    folk
    -0.80
    mond
    -0.78
    robe
    -0.78
    aiden
    -0.78
    prototype
    -0.77
    vest
    -0.75
    gart
    -0.74
    POSITIVE LOGITS
     ILCS
    0.76
     carbohyd
    0.74
    aution
    0.69
    190
    0.69
    kHz
    0.68
    ĸļ
    0.68
    uador
    0.68
     kHz
    0.67
     Hond
    0.67
     Deg
    0.67
    Activations Density 0.021%

    No Known Activations