© 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. 8-RES-JB
    11. 6068
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational and organizational entities, particularly schools and districts

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and governance structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aphael
    -0.76
    Ô
    -0.75
    hots
    -0.71
     Detected
    -0.69
    phies
    -0.67
    ynthesis
    -0.67
    alys
    -0.66
    NetMessage
    -0.66
    amia
    -0.66
    cious
    -0.66
    POSITIVE LOGITS
     inspector
    1.03
     administrator
    1.00
     attorney
    1.00
     commissioner
    0.95
     solicitor
    0.95
     superintendent
    0.90
     clerk
    0.89
     regulator
    0.88
     secretary
    0.88
     Registrar
    0.86
    Activations Density 0.319%

    No Known Activations