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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7048
    Prev
    Next
    INDEX
    Explanations

    mentions of school-related activities or events

    oai_token-act-pair · gpt-3.5-turbo

    references to formal education institutions and their official actions

    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
    sson
    -0.87
     prophe
    -0.78
     predictions
    -0.78
    optim
    -0.75
    PsyNetMessage
    -0.71
    ertodd
    -0.71
    psey
    -0.69
    omics
    -0.69
    lust
    -0.69
    apest
    -0.68
    POSITIVE LOGITS
     disciplinary
    1.52
     reprim
    1.48
     discipl
    1.37
     apologized
    1.33
     rescind
    1.26
     revoked
    1.23
     suspended
    1.22
     disciplined
    1.16
     administrators
    1.12
     terminated
    1.11
    Activations Density 0.569%

    No Known Activations