© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 10056
    Prev
    Next
    INDEX
    Explanations

    phrases related to urging or advising action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "urge" and its variations in the context of calling for actions or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.81
    çĦ
    -0.76
    ccording
    -0.69
    philis
    -0.68
    frac
    -0.67
    ãĤ¡
    -0.66
    ãĤ©
    -0.65
    erenn
    -0.65
    nown
    -0.64
    ãĤ´
    -0.64
    POSITIVE LOGITS
     caution
    1.27
     patience
    1.08
     restraint
    1.07
     listeners
    1.06
     readers
    1.02
     viewers
    0.98
     followers
    0.97
     policymakers
    0.93
     lawmakers
    0.92
     vigilance
    0.89
    Activations Density 0.066%

    No Known Activations