© 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. 2138
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days or phases

    oai_token-act-pair · gpt-3.5-turbo

    references to specific phases or stages, particularly those labeled as "one" or "two."

    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
    achu
    -0.71
    astical
    -0.64
     Happ
    -0.64
    Board
    -0.63
     Society
    -0.61
    ropolitan
    -0.61
     Groups
    -0.60
    idences
    -0.60
    raltar
    -0.59
    VOL
    -0.59
    POSITIVE LOGITS
     hundred
    0.63
     offender
    0.61
     erad
    0.59
     thousand
    0.59
    ¶ħ
    0.58
     recogn
    0.58
    aciously
    0.58
    SPONSORED
    0.58
     Hundred
    0.57
     containment
    0.57
    Activations Density 0.045%

    No Known Activations