© 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. 22521
    Prev
    Next
    INDEX
    Explanations

    dates and years

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the initiation of actions or activities

    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
     ILCS
    -0.79
    arta
    -0.79
    arest
    -0.72
    imilar
    -0.70
    jad
    -0.68
    pter
    -0.66
    tta
    -0.66
    _-
    -0.66
    ĪĴ
    -0.64
    itably
    -0.63
    POSITIVE LOGITS
     functioning
    1.25
     operating
    1.09
     airing
    1.09
     operation
    1.07
     operations
    1.04
     selling
    1.01
     accepting
    1.00
     operate
    0.97
     broadcasting
    0.95
     delivering
    0.94
    Activations Density 0.100%

    No Known Activations