© 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. 20278
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Should."

    oai_token-act-pair · gpt-3.5-turbo

    questions or propositions that begin with "Should."

    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
    stood
    -0.75
     Finder
    -0.71
    cule
    -0.62
     sclerosis
    -0.62
     Puzzle
    -0.61
     Fra
    -0.61
     Vers
    -0.61
    atile
    -0.61
     Resistance
    -0.59
     Bomb
    -0.59
    POSITIVE LOGITS
    ering
    1.01
    ered
    0.99
    ĪĴ
    0.83
    icum
    0.83
     be
    0.82
    n
    0.82
    edi
    0.80
    arget
    0.78
    uel
    0.78
    ouch
    0.76
    Activations Density 0.042%

    No Known Activations