© 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. 4-RES-JB
    11. 19762
    Prev
    Next
    INDEX
    Explanations

    phrases related to quick actions or responses

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "swift" and its variations in context

    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
    gdala
    -0.91
    izons
    -0.73
    ovember
    -0.72
    ortium
    -0.67
    aples
    -0.67
    arettes
    -0.65
    pheus
    -0.65
    agine
    -0.64
    mingham
    -0.63
    park
    -0.63
    POSITIVE LOGITS
    itude
    1.04
    ness
    1.00
    idious
    0.97
     swift
    0.96
    nesses
    0.95
    aneously
    0.94
     succession
    0.84
    eness
    0.82
    motion
    0.80
     response
    0.80
    Activations Density 0.021%

    No Known Activations