© 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. 11-RES-JB
    11. 11435
    Prev
    Next
    INDEX
    Explanations

    mentions directed at the user, typically indicating actions they can take or benefits they can receive

    oai_token-act-pair · gpt-3.5-turbo

    second-person pronouns and phrases addressing the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENDED
    -0.69
    pite
    -0.68
    ensable
    -0.68
    pires
    -0.65
    soType
    -0.62
    amaz
    -0.62
     millenn
    -0.61
    ¿½
    -0.60
     Failure
    -0.59
     pathological
    -0.59
    POSITIVE LOGITS
    'll
    1.52
    're
    1.41
     can
    1.23
    've
    1.12
     get
    1.09
     won
    1.00
    'd
    0.98
     don
    0.98
     gain
    0.96
     aren
    0.95
    Activations Density 0.147%

    No Known Activations