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

    Neuronpedia

    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. 23518
    Prev
    Next
    INDEX
    Explanations

    specific instructions or actions directed towards the user in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    second-person pronouns and actions directed towards the user

    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
    adium
    -0.72
    polit
    -0.66
     confessions
    -0.63
    ¿½
    -0.63
    geries
    -0.59
    Cra
    -0.59
    ivism
    -0.58
    hearted
    -0.57
     Shelby
    -0.57
    ICE
    -0.56
    POSITIVE LOGITS
    'll
    1.43
    're
    1.28
     can
    1.24
     need
    1.23
     MUST
    1.17
    've
    1.08
     must
    1.08
     may
    1.07
     cannot
    1.03
     should
    1.00
    Activations Density 0.126%

    No Known Activations