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

    Neuronpedia

    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. 9-RES-JB
    11. 8931
    Prev
    Next
    INDEX
    Explanations

    words related to authority or power

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific suffixes or patterns in words, particularly combinations of letters that follow a recurring or distinctive format

    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
    ecided
    -0.62
    ocobo
    -0.59
     displ
    -0.58
    ikh
    -0.58
     Alban
    -0.57
     Kron
    -0.57
     gears
    -0.56
    ngth
    -0.56
     Dialogue
    -0.56
    yip
    -0.55
    POSITIVE LOGITS
    ÃĽ
    0.88
    dash
    0.81
    oir
    0.80
    uration
    0.78
    ailable
    0.77
    afia
    0.76
    EMENT
    0.75
    ements
    0.74
    ement
    0.73
    ment
    0.70
    Activations Density 0.086%

    No Known Activations