© 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. 17250
    Prev
    Next
    INDEX
    Explanations

    phrases related to lack of change or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of signs or indicators of various conditions or situations

    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
    ahime
    -0.78
    halla
    -0.68
    ISH
    -0.66
    adish
    -0.63
    adelphia
    -0.62
    ARY
    -0.61
    lda
    -0.60
    rior
    -0.60
    ISO
    -0.60
    ategory
    -0.59
    POSITIVE LOGITS
     Signs
    0.98
     signs
    0.95
    posts
    0.87
    atories
    0.86
    igmatic
    0.83
    ifact
    0.78
    emic
    0.77
    matic
    0.75
    oresc
    0.75
    trump
    0.72
    Activations Density 0.017%

    No Known Activations