© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19085
    Prev
    Next
    INDEX
    Explanations

    phrases questioning beliefs, values, and actions

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements related to choices and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Prim
    -0.63
     Pap
    -0.59
    ombat
    -0.59
    BALL
    -0.58
    iard
    -0.58
    ((
    -0.58
     9000
    -0.57
     Tib
    -0.56
    Dri
    -0.56
     630
    -0.56
    POSITIVE LOGITS
    iety
    0.82
     aspire
    0.73
     degrade
    0.70
     threaten
    0.70
     innovate
    0.69
     pray
    0.68
     worsen
    0.68
     prosper
    0.67
    morrow
    0.66
     feared
    0.66
    Activations Density 0.231%

    No Known Activations