© 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. 7-RES-JB
    11. 2963
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific time or duration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "During"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettle
    -0.71
    ITH
    -0.70
    usercontent
    -0.67
    NRS
    -0.67
    ards
    -0.67
    adr
    -0.64
    onica
    -0.64
    inguishable
    -0.63
    onet
    -0.63
    ugu
    -0.63
    POSITIVE LOGITS
     periods
    0.83
     daylight
    0.82
     weekends
    0.78
     halftime
    0.77
     times
    0.74
     conversations
    0.73
     ceremonies
    0.73
    ventory
    0.73
     wartime
    0.72
     renovations
    0.71
    Activations Density 0.028%

    No Known Activations