© 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. 17153
    Prev
    Next
    INDEX
    Explanations

    numerical scores or results in a competitive context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of scores in competitive 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
    xon
    -0.73
    agan
    -0.66
    LECT
    -0.64
    tan
    -0.62
    regon
    -0.61
     mil
    -0.61
     colonization
    -0.61
     carcin
    -0.60
     suitcase
    -0.60
     mascul
    -0.59
    POSITIVE LOGITS
    keeper
    1.21
    card
    1.14
    cards
    1.12
    keepers
    1.03
    ific
    0.90
    esses
    0.86
    emi
    0.86
    aments
    0.85
    rs
    0.85
    keeping
    0.84
    Activations Density 0.015%

    No Known Activations