© 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. 9-RES-JB
    11. 3501
    Prev
    Next
    INDEX
    Explanations

    questions asking for opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    questions or statements expressing beliefs or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yna
    -0.98
    iona
    -0.74
    inar
    -0.73
    eding
    -0.72
    irement
    -0.72
     pione
    -0.71
    cue
    -0.65
    kw
    -0.64
    ÃŃa
    -0.64
    ancing
    -0.62
    POSITIVE LOGITS
    phas
    0.75
     it
    0.75
     differently
    0.74
     there
    0.71
     passionately
    0.69
    fully
    0.69
     that
    0.66
     merit
    0.65
     strongly
    0.65
     tanks
    0.63
    Activations Density 0.117%

    No Known Activations