© 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. 10-RES-JB
    11. 16939
    Prev
    Next
    INDEX
    Explanations

    Twitter handles (usernames) related to various individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    elements related to social media and online interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     caring
    -0.67
     discern
    -0.64
     felon
    -0.60
     sanctions
    -0.60
     appeals
    -0.58
     scratches
    -0.58
     afore
    -0.58
     loosely
    -0.58
     personalized
    -0.58
     prescribed
    -0.57
    POSITIVE LOGITS
    zx
    1.23
    yg
    1.20
    CN
    1.17
    OY
    1.17
    ZX
    1.17
    YC
    1.15
    Iv
    1.14
    qq
    1.14
    dq
    1.14
    CV
    1.14
    Activations Density 0.067%

    No Known Activations