© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14592
    Prev
    Next
    INDEX
    Explanations

    actions that can be taken or permissions granted in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "can" and its variations to indicate ability or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.69
    din
    -0.62
    interstitial
    -0.61
    cedented
    -0.61
    Maker
    -0.61
    Dur
    -0.60
     Critics
    -0.57
    awei
    -0.57
    pection
    -0.56
     BAL
    -0.56
    POSITIVE LOGITS
    't
    1.37
     choose
    1.13
     decide
    1.10
    adian
    1.07
     optionally
    1.03
     afford
    1.02
     easily
    1.02
     nominate
    0.99
    NOT
    0.97
     freely
    0.96
    Activations Density 0.207%

    No Known Activations