© 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. 4-RES-JB
    11. 20864
    Prev
    Next
    INDEX
    Explanations

    phrases indicating blame or responsibility in a situation

    oai_token-act-pair · gpt-3.5-turbo

    repeated pronouns and forms of the verb "to be"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Peak
    -0.78
    tains
    -0.66
     Unlimited
    -0.66
    Outside
    -0.64
    earch
    -0.64
     Outside
    -0.63
     Previous
    -0.62
    age
    -0.58
    noon
    -0.58
    pires
    -0.56
    POSITIVE LOGITS
    'll
    0.93
    're
    0.83
    've
    0.81
    ARB
    0.80
    'd
    0.72
    cause
    0.69
     hereby
    0.68
    razil
    0.68
    selves
    0.68
    pherd
    0.67
    Activations Density 0.526%

    No Known Activations