© 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. 11-RES-JB
    11. 21236
    Prev
    Next
    INDEX
    Explanations

    quantitative information and data points

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and terms related to statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Talks
    -0.77
     Defeat
    -0.76
     Flavoring
    -0.72
    cknow
    -0.68
    osi
    -0.66
     Trailer
    -0.66
     Quit
    -0.65
    rench
    -0.65
     Teach
    -0.64
    emis
    -0.63
    POSITIVE LOGITS
     skewed
    1.29
     inflated
    1.27
     computed
    1.24
     calculated
    1.22
     adjusted
    1.17
     estimates
    1.13
     accurate
    1.13
     inaccurate
    1.10
     approximate
    1.09
     extrap
    1.07
    Activations Density 0.198%

    No Known Activations