© 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. 15711
    Prev
    Next
    INDEX
    Explanations

    phrases related to interaction and interconnection

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of words related to interconnectedness or interactivity

    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
    WARD
    -0.57
     Soda
    -0.56
     TAMADRA
    -0.56
    Rich
    -0.54
     Feast
    -0.54
    cats
    -0.54
     Cly
    -0.54
    steen
    -0.54
    atten
    -0.54
     wolf
    -0.53
    POSITIVE LOGITS
    xual
    1.17
    poral
    1.07
    imensional
    1.01
    etary
    1.01
    incial
    0.99
    ricular
    0.96
    perse
    0.94
    allic
    0.90
    relations
    0.90
    utory
    0.89
    Activations Density 0.080%

    No Known Activations