© 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. 2801
    Prev
    Next
    INDEX
    Explanations

    comparisons between quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    comparative statistics and quantifiable data references

    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
    ocy
    -0.59
    Journal
    -0.59
     Things
    -0.59
    journal
    -0.58
     Days
    -0.57
    Contribut
    -0.57
    idav
    -0.57
    piring
    -0.56
    nen
    -0.56
     enthus
    -0.56
    POSITIVE LOGITS
     double
    1.17
     twice
    1.15
     doubled
    1.12
     doubling
    1.10
     tripled
    1.07
     triple
    1.04
     quadru
    1.01
     half
    0.99
    thirds
    0.94
     doubles
    0.94
    Activations Density 0.112%

    No Known Activations