© 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. 24498
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Pass" followed by a numerical value, possibly related to passes or permissions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Pass" in various contexts

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.96
    ä¸ī
    -0.75
     GOODMAN
    -0.66
     nutshell
    -0.62
     Tycoon
    -0.61
     GEAR
    -0.60
     Kut
    -0.60
     Ruler
    -0.60
     Milk
    -0.59
     lord
    -0.59
    POSITIVE LOGITS
    engers
    1.50
    enger
    1.30
    wd
    1.22
    ioned
    1.05
    aic
    1.03
    words
    1.03
    es
    0.99
    phrase
    0.96
    ports
    0.95
    ences
    0.95
    Activations Density 0.020%

    No Known Activations