© 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. 7082
    Prev
    Next
    INDEX
    Explanations

    terms related to competitions and qualifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to qualifiers and single-player contexts

    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
    atana
    -0.79
    ury
    -0.74
    ī
    -0.72
     detrim
    -0.71
    arma
    -0.67
    oint
    -0.67
    lyak
    -0.67
    ģ
    -0.67
    azaki
    -0.67
    ern
    -0.66
    POSITIVE LOGITS
    ifiers
    0.93
    ifier
    0.78
    fect
    0.73
    ãĤ§
    0.70
    pace
    0.69
     berth
    0.69
    verse
    0.67
    hom
    0.66
    bucks
    0.65
    ference
    0.64
    Activations Density 0.038%

    No Known Activations