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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 10590
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Can I" or "How can I"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the first-person pronoun "I" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tions
    -0.70
    ij士
    -0.69
     Guns
    -0.67
     Debor
    -0.67
    inery
    -0.64
     Roose
    -0.61
    ãĤ¦ãĤ¹
    -0.61
     Sharp
    -0.60
     corridors
    -0.60
    iors
    -0.59
    POSITIVE LOGITS
    ?'
    0.88
    ?'"
    0.81
    ?
    0.80
    ?????
    0.79
     suppose
    0.78
    ???
    0.76
     presume
    0.75
    ??
    0.74
    ????
    0.74
    ...?
    0.74
    Activations Density 0.052%

    No Known Activations