© 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. 16343
    Prev
    Next
    INDEX
    Explanations

    phrases related to arranging or scheduling activities and tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to picking up or collecting

    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
     disclaimer
    -0.63
     gh
    -0.62
     Austral
    -0.61
     Greenwich
    -0.59
     apologies
    -0.59
     Glob
    -0.58
     fid
    -0.57
     omission
    -0.57
    ĸļ
    -0.57
     imperative
    -0.56
    POSITIVE LOGITS
    axe
    0.87
    cho
    0.82
    pocket
    0.82
    une
    0.81
    picking
    0.79
    kn
    0.78
    artist
    0.75
    pun
    0.72
    laughter
    0.71
    Brow
    0.70
    Activations Density 0.056%

    No Known Activations