© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    mentions of breaking records, surpassing previous marks, or achieving high scores

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to record-breaking achievements

    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
    arty
    -0.81
    opoulos
    -0.74
    lik
    -0.70
     seasoning
    -0.69
    sbm
    -0.69
     acquaint
    -0.69
    Pros
    -0.68
     sparing
    -0.67
    )=(
    -0.67
    ifferent
    -0.67
    POSITIVE LOGITS
     Guinness
    1.45
     surpassed
    1.25
     surpass
    1.16
     feat
    1.11
     record
    1.09
     records
    1.05
     milestone
    1.03
     eclips
    1.02
    record
    1.00
     achieved
    0.97
    Activations Density 0.307%

    No Known Activations