© 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. 21995
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "li" followed by a number indicating the strength of activation for these sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to lists or items in a structured format

    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
    mble
    -0.79
     Debor
    -0.78
    byss
    -0.72
    bucks
    -0.70
    lain
    -0.69
    eers
    -0.69
     Cosponsors
    -0.67
    ilater
    -0.67
    swing
    -0.67
    locks
    -0.67
    POSITIVE LOGITS
    utenant
    1.17
    zzle
    1.12
    ptin
    1.10
    udic
    0.98
    uci
    0.95
    pper
    0.88
    orno
    0.88
    ibrary
    0.86
    pton
    0.84
    ars
    0.83
    Activations Density 0.015%

    No Known Activations