© 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. 2737
    Prev
    Next
    INDEX
    Explanations

    financial values and dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical data and statistics, particularly involving time and measurements

    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
    ullah
    -0.65
    \<
    -0.64
    too
    -0.63
    untled
    -0.61
     UFOs
    -0.60
    atom
    -0.59
    '-
    -0.58
    mill
    -0.56
     balk
    -0.55
    Ay
    -0.55
    POSITIVE LOGITS
     peak
    0.72
     midday
    0.71
     Friday
    0.68
     avg
    0.67
    daq
    0.67
     lows
    0.66
     compared
    0.66
    elsen
    0.64
     Thursday
    0.64
     kickoff
    0.64
    Activations Density 0.175%

    No Known Activations