© 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. 2670
    Prev
    Next
    INDEX
    Explanations

    recent events or developments

    oai_token-act-pair · gpt-3.5-turbo

    references to specific significant events or incidents

    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
    itu
    -0.68
    berries
    -0.68
    ngth
    -0.66
    姫
    -0.65
    66666666
    -0.65
    aimon
    -0.65
    imi
    -0.64
     existed
    -0.60
    ãĥīãĥ©
    -0.60
    pots
    -0.59
    POSITIVE LOGITS
     culmination
    1.56
     latest
    1.34
     result
    1.15
     longest
    1.14
     largest
    1.14
     centerpiece
    1.09
     deadliest
    1.08
     first
    1.06
     heaviest
    1.05
     biggest
    1.02
    Activations Density 0.152%

    No Known Activations