© 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. 6-RES-JB
    11. 401
    Prev
    Next
    INDEX
    Explanations

    individual words or short phrases related to administrative or procedural terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sections or parts of a content piece

    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
    berus
    -0.69
    apons
    -0.67
     groom
    -0.63
     elbows
    -0.63
     Commissioners
    -0.60
    ãĤī
    -0.60
    ministic
    -0.59
    ITH
    -0.59
     minded
    -0.59
     sugg
    -0.56
    POSITIVE LOGITS
    icularly
    1.16
    ially
    1.15
    ners
    1.13
    icipated
    1.00
    nered
    1.00
    icular
    0.97
    ner
    0.96
    ials
    0.93
    ridge
    0.90
    isans
    0.88
    Activations Density 0.039%

    No Known Activations