© 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 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. 6-RES-JB
    11. 17738
    Prev
    Next
    INDEX
    Explanations

    occurrences of contractions with "n't"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of prohibition or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veins
    -0.74
     continents
    -0.65
    NetMessage
    -0.64
     vein
    -0.63
     trails
    -0.62
     landscapes
    -0.60
    hole
    -0.58
    holes
    -0.58
     cores
    -0.58
     Wid
    -0.58
    POSITIVE LOGITS
     emulate
    0.88
    arent
    0.75
    reated
    0.72
     disclose
    0.71
    regnancy
    0.71
     behave
    0.70
    ilege
    0.69
     be
    0.69
    imize
    0.69
    ention
    0.69
    Activations Density 0.062%

    No Known Activations