© 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. 17425
    Prev
    Next
    INDEX
    Explanations

    terms related to executive positions or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to executives and evacuations

    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
    bones
    -0.70
    bone
    -0.69
     Flavoring
    -0.69
     Leilan
    -0.68
    BALL
    -0.66
    theless
    -0.66
    farm
    -0.65
    hift
    -0.64
     Apost
    -0.62
     Fif
    -0.62
    POSITIVE LOGITS
    utions
    1.97
    uting
    1.89
    ution
    1.81
    utive
    1.72
    utable
    1.62
    uating
    1.61
    utes
    1.59
    uations
    1.56
    uments
    1.55
    uted
    1.54
    Activations Density 0.086%

    No Known Activations