© 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. 10-RES-JB
    11. 24017
    Prev
    Next
    INDEX
    Explanations

    phrases related to privacy and confidential information

    oai_token-act-pair · gpt-3.5-turbo

    references to privacy and privileged information

    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
    grass
    -0.69
    LER
    -0.67
     Legion
    -0.65
     conver
    -0.64
    ORN
    -0.63
     Gentle
    -0.62
    eric
    -0.62
     spur
    -0.61
     composed
    -0.61
     composing
    -0.60
    POSITIVE LOGITS
    ilege
    1.75
    ileged
    1.62
    ately
    1.33
    acies
    1.31
    acy
    1.12
    aband
    1.09
    atile
    1.05
    atis
    0.98
    ilage
    0.98
    acist
    0.97
    Activations Density 0.036%

    No Known Activations