© 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. 11038
    Prev
    Next
    INDEX
    Explanations

    numerical values related to goals, targets, records, and milestones

    oai_token-act-pair · gpt-3.5-turbo

    key performance indicators and numerical benchmarks

    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
    âĹ¼
    -0.70
     incorpor
    -0.67
    minster
    -0.67
     specialize
    -0.62
     Matters
    -0.61
    NetMessage
    -0.60
    versive
    -0.59
    Ô
    -0.59
    çīĪ
    -0.58
     differe
    -0.58
    POSITIVE LOGITS
     threshold
    0.79
     (~
    0.77
     cutoff
    0.76
     achievable
    0.75
     ($
    0.75
     limit
    0.74
     of
    0.73
     allowable
    0.72
     (>
    0.72
     reached
    0.72
    Activations Density 0.209%

    No Known Activations