© 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. 7-RES-JB
    11. 16734
    Prev
    Next
    INDEX
    Explanations

    references to specific versions of JavaScript ES (ECMAScript)

    oai_token-act-pair · gpt-3.5-turbo

    references to ECMAScript (ES) versions and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yright
    -0.77
    ysis
    -0.74
    zzle
    -0.73
    tons
    -0.70
    ãĥĥãĥĪ
    -0.70
    geries
    -0.67
    olulu
    -0.67
    ing
    -0.67
    zers
    -0.66
    uddin
    -0.66
    POSITIVE LOGITS
    TERN
    1.25
    SE
    1.07
    QUIRE
    1.03
    FIN
    1.02
    FI
    1.01
    SAY
    1.01
    Xi
    1.00
    CAP
    0.96
    ENS
    0.95
    ASY
    0.95
    Activations Density 0.028%

    No Known Activations