© 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. 11-RES-JB
    11. 9914
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress or completion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to improvement or development over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.86
    ĸļ
    -0.79
    deen
    -0.79
    ntil
    -0.77
    ailability
    -0.77
     Palestin
    -0.73
    everal
    -0.72
     oun
    -0.71
     Parables
    -0.69
     Aires
    -0.68
    POSITIVE LOGITS
     Ez
    0.57
     q
    0.53
     ...
    0.53
     gmaxwell
    0.52
     crew
    0.51
     pawn
    0.51
    inx
    0.51
     cy
    0.49
     rel
    0.49
     dish
    0.48
    Activations Density 0.123%

    No Known Activations