© 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. 20238
    Prev
    Next
    INDEX
    Explanations

    phrases related to numbers and measurements, specifically with a focus on "double" or "digit"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic downturns and financial crises

    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
     EntityItem
    -0.72
     lest
    -0.67
     physic
    -0.61
    ðŁĺ
    -0.61
     greatly
    -0.58
     Zar
    -0.58
     Parenthood
    -0.58
     "$:/
    -0.58
     perce
    -0.57
     knowing
    -0.57
    POSITIVE LOGITS
    edged
    1.38
    digit
    1.33
    sided
    1.22
    double
    1.15
    duty
    1.12
    faced
    1.07
    checking
    1.02
    dose
    1.02
    edge
    1.02
    cross
    1.01
    Activations Density 0.032%

    No Known Activations