© 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. 14028
    Prev
    Next
    INDEX
    Explanations

    numerical quantities and units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    quantities and numerical data

    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
    actionDate
    -0.77
    ablishment
    -0.71
     RELEASE
    -0.70
    estine
    -0.67
     guiActiveUnfocused
    -0.67
    eteria
    -0.66
    eworld
    -0.66
    sole
    -0.65
    ieu
    -0.65
     Played
    -0.64
    POSITIVE LOGITS
     kilograms
    1.35
     pounds
    1.29
     grams
    1.25
     gallons
    1.23
     ounces
    1.22
    lbs
    1.15
     pieces
    1.12
     lbs
    1.11
     acres
    1.07
     bottles
    1.07
    Activations Density 0.200%

    No Known Activations