© 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. 12915
    Prev
    Next
    INDEX
    Explanations

    large numbers, particularly financial figures

    oai_token-act-pair · gpt-3.5-turbo

    references to financial figures and monetary values

    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
     srfAttach
    -0.74
    ornings
    -0.73
    dinand
    -0.66
    Insp
    -0.65
    licensed
    -0.63
    olph
    -0.63
    intendent
    -0.63
    tainment
    -0.62
    ingo
    -0.62
    orously
    -0.61
    POSITIVE LOGITS
     mark
    1.22
     figure
    1.07
     allotted
    0.99
     limit
    0.99
     threshold
    0.98
     discrepancy
    0.91
     gap
    0.91
     shortfall
    0.90
     cutoff
    0.90
     range
    0.90
    Activations Density 0.165%

    No Known Activations