© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 24374
    Prev
    Next
    INDEX
    Explanations

    numbers related to age, time, weight, or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to age, time, and weight

    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
     pse
    -0.77
     util
    -0.70
     organis
    -0.67
     territ
    -0.67
    xit
    -0.66
     analys
    -0.64
    Laun
    -0.63
     Reply
    -0.61
    Intern
    -0.61
     whilst
    -0.61
    POSITIVE LOGITS
     mph
    1.07
     pounds
    0.92
     miles
    0.91
     grams
    0.89
     ounces
    0.86
     minutes
    0.84
     gallons
    0.83
     feet
    0.81
     volts
    0.80
     cents
    0.79
    Activations Density 0.201%

    No Known Activations