© 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. 1-RES-JB
    11. 20076
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical exercises and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to exercise techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embr
    -0.66
     peach
    -0.66
    saw
    -0.65
     distingu
    -0.64
    士
    -0.64
     aven
    -0.64
    åħī
    -0.63
     corpus
    -0.62
     mango
    -0.62
    ufact
    -0.62
    POSITIVE LOGITS
    asio
    0.74
    roman
    0.74
    yz
    0.71
    tails
    0.71
    TL
    0.70
    hern
    0.68
    pite
    0.67
    QB
    0.67
    ENC
    0.66
    security
    0.66
    Activations Density 0.000%

    No Known Activations