© 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. 21238
    Prev
    Next
    INDEX
    Explanations

    phrases related to arranging or organizing activities or objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to "pickup."

    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
    ĸļ
    -0.81
     Fi
    -0.64
    enegger
    -0.61
    ITNESS
    -0.58
    ARY
    -0.56
     Reader
    -0.55
     Cornell
    -0.55
     beh
    -0.54
     hello
    -0.53
     Found
    -0.53
    POSITIVE LOGITS
    axe
    1.04
    six
    0.97
    une
    0.82
    angles
    0.81
    ussen
    0.79
    option
    0.79
    kn
    0.78
    me
    0.78
    two
    0.78
    cho
    0.77
    Activations Density 0.056%

    No Known Activations