© 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. 7444
    Prev
    Next
    INDEX
    Explanations

    mentions of actions or events happening after some specific time point

    oai_token-act-pair · gpt-3.5-turbo

    references to the duration of time or events that happen after specified periods

    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
    erial
    -0.74
    eh
    -0.72
    pac
    -0.72
    RGB
    -0.71
    enos
    -0.70
    eyes
    -0.69
    Put
    -0.69
    ARDIS
    -0.69
     indoors
    -0.69
    ãĥ¼ãĤ¯
    -0.69
    POSITIVE LOGITS
     disgrace
    0.93
     disagreements
    0.89
     dishon
    0.84
     unsatisf
    0.84
     citing
    0.82
     scathing
    0.71
     disple
    0.71
     disagreement
    0.70
     resign
    0.69
     controversy
    0.69
    Activations Density 0.288%

    No Known Activations