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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3708
    Prev
    Next
    INDEX
    Explanations

    proper nouns and submissions related to an archive or database called "Sub9."

    oai_token-act-pair · gpt-3.5-turbo

    references to subscriptions or submission acknowledgments

    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
    OHN
    -0.77
     Cors
    -0.77
    ILLE
    -0.76
     Papers
    -0.74
    INESS
    -0.74
     Zurich
    -0.73
     Dol
    -0.72
    20439
    -0.71
     fir
    -0.71
    çİĭ
    -0.70
    POSITIVE LOGITS
    mitted
    1.54
    sequent
    1.50
    sequently
    1.45
    stantial
    1.36
    ordinate
    1.28
    mitting
    1.26
    missive
    1.25
    verting
    1.24
    scription
    1.20
    missions
    1.15
    Activations Density 0.015%

    No Known Activations