© 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. 24562
    Prev
    Next
    INDEX
    Explanations

    words related to administrative processes and legal procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to administrative functions and processes

    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
    IDER
    -0.68
     Canary
    -0.67
    INTER
    -0.66
     bott
    -0.66
     Jub
    -0.64
    isations
    -0.63
    isi
    -0.61
    mith
    -0.61
     JPM
    -0.61
     advoc
    -0.60
    POSITIVE LOGITS
    ration
    2.27
    rative
    2.22
    rator
    2.20
    rations
    2.11
    rators
    2.10
    rating
    2.09
    rated
    1.97
    rates
    1.96
    rals
    1.87
    rate
    1.84
    Activations Density 0.137%

    No Known Activations