© 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. 11556
    Prev
    Next
    INDEX
    Explanations

    food-related words, particularly those related to a meal like lunch

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "unch" in words

    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
     ministry
    -0.77
    âĹ¼
    -0.77
    wcs
    -0.73
    Naz
    -0.66
     Scientology
    -0.63
    lling
    -0.63
     differe
    -0.63
    Offic
    -0.63
    tnc
    -0.62
     Defenders
    -0.61
    POSITIVE LOGITS
    arted
    0.94
    ainment
    0.88
    atters
    0.87
    ramid
    0.87
    ies
    0.86
    osate
    0.86
    iesta
    0.85
    ifact
    0.83
    aus
    0.83
    onen
    0.82
    Activations Density 0.033%

    No Known Activations