© 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. 7-RES-JB
    11. 6397
    Prev
    Next
    INDEX
    Explanations

    phrases related to staying away from a particular place or activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to avoiding or staying away from something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¾
    -0.84
    ¥
    -0.72
     testament
    -0.69
     retaining
    -0.67
    upon
    -0.64
    ELS
    -0.63
    olars
    -0.62
     Congratulations
    -0.61
     extracted
    -0.60
    arily
    -0.60
    POSITIVE LOGITS
    sites
    0.72
    ake
    0.69
    agne
    0.68
    ulnerable
    0.68
    enged
    0.67
    amia
    0.67
    Ïī
    0.66
    chuk
    0.66
     anymore
    0.66
    cliffe
    0.65
    Activations Density 0.059%

    No Known Activations