© 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. 12762
    Prev
    Next
    INDEX
    Explanations

    references to numerical milestones or achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to individual achievements and game statistics in sports

    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
    vine
    -0.67
    hyde
    -0.67
    cephal
    -0.63
    spir
    -0.62
    scape
    -0.62
    javascript
    -0.62
    ablishment
    -0.60
     wielding
    -0.58
    cker
    -0.58
    Texture
    -0.57
    POSITIVE LOGITS
     own
    1.27
     first
    1.10
     third
    0.96
     entire
    0.94
     usual
    0.92
     fifth
    0.91
     fourth
    0.91
     customary
    0.90
     eighth
    0.90
     FIRST
    0.90
    Activations Density 0.131%

    No Known Activations