© 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. 24042
    Prev
    Next
    INDEX
    Explanations

    action verbs related to human behavior

    oai_token-act-pair · gpt-3.5-turbo

    actions related to consumption and product use

    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
     millenn
    -0.86
     unanim
    -0.61
     Pere
    -0.60
     Vul
    -0.59
     Kle
    -0.58
     Gunn
    -0.58
     Gree
    -0.57
     coercive
    -0.57
     unlaw
    -0.57
     protracted
    -0.56
    POSITIVE LOGITS
    */(
    0.82
    ;
    0.77
    .
    0.76
     ('
    0.75
     WITHOUT
    0.73
     ("
    0.71
    .:
    0.71
    .*
    0.71
    *.
    0.70
    ient
    0.70
    Activations Density 0.196%

    No Known Activations