© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1582
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to actions and commands

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to evaluation and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phased
    -0.60
    icer
    -0.57
    atus
    -0.54
     unbeat
    -0.54
    76561
    -0.54
    iann
    -0.54
    rolling
    -0.54
     Andersen
    -0.53
     similarly
    -0.52
    ributed
    -0.50
    POSITIVE LOGITS
     alike
    0.84
    ––
    0.77
    !,
    0.75
    !/
    0.72
    ,.
    0.68
     etc
    0.67
    !.
    0.64
    SPONSORED
    0.63
    ;
    0.63
    ,,,,
    0.63
    Activations Density 0.828%

    No Known Activations