© 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. 7-RES-JB
    11. 2238
    Prev
    Next
    INDEX
    Explanations

    mentions of "Gen" followed by a number, possibly associated with a specific generation or group

    oai_token-act-pair · gpt-3.5-turbo

    references to genetic topics and events, particularly related to "Gen" as a prefix

    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
    TPPStreamerBot
    -0.70
    anwhile
    -0.68
    ħĭ
    -0.65
    letal
    -0.65
    ngth
    -0.63
    landish
    -0.63
    eneg
    -0.62
    SourceFile
    -0.62
    ï¸
    -0.61
     Heard
    -0.61
    POSITIVE LOGITS
    uine
    1.27
    ocide
    1.25
    iuses
    1.21
    omics
    1.04
    otype
    1.03
    omic
    1.02
    istries
    0.95
    alogy
    0.95
    omes
    0.92
    etically
    0.91
    Activations Density 0.020%

    No Known Activations