© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RES-JB
    11. 12972
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or commands with verbs and numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express suggestions or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     promoted
    -0.69
     disliked
    -0.67
     ejected
    -0.66
     Mirage
    -0.66
     preferred
    -0.66
     targeted
    -0.65
     Modified
    -0.65
     hurled
    -0.64
     assigned
    -0.64
     relative
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.08
    say
    1.06
    him
    1.02
    s
    0.97
     denote
    0.96
    be
    0.95
    them
    0.94
    speak
    0.93
    uers
    0.91
    sing
    0.90
    Activations Density 0.049%

    No Known Activations