© 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. 4-RES-JB
    11. 9603
    Prev
    Next
    INDEX
    Explanations

    verbs related to intention or desire

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire and need

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

    No Comments

    Negative Logits
    ////////////////
    -0.46
     Eh
    -0.45
    arrell
    -0.44
     Zup
    -0.44
    Comments
    -0.43
     Shap
    -0.43
     Retro
    -0.42
    âĸijâĸij
    -0.42
     Hard
    -0.41
     caveats
    -0.41
    POSITIVE LOGITS
     perceive
    0.47
     actually
    0.46
     personally
    0.45
    entimes
    0.44
     consume
    0.44
     otherwise
    0.43
    ucha
    0.42
    strap
    0.42
     legitimately
    0.42
     unwittingly
    0.41
    Activations Density 0.993%

    No Known Activations