© 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. 12765
    Prev
    Next
    INDEX
    Explanations

    the use of ordinal numbers in a list

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rankings or top positions in various contexts

    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
     Lauder
    -0.73
    ajor
    -0.66
    ATIONS
    -0.64
    pty
    -0.63
    vm
    -0.62
    cation
    -0.62
    thens
    -0.61
    md
    -0.60
    anism
    -0.60
    oise
    -0.59
    POSITIVE LOGITS
    most
    1.05
     earners
    1.04
     notch
    1.01
     contenders
    1.00
     priority
    0.96
     tier
    0.94
     scorer
    0.93
    ographical
    0.93
     priorities
    0.92
     performers
    0.91
    Activations Density 0.043%

    No Known Activations