© 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. 23245
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing activities or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing actions or processes

    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
    uminati
    -0.77
    iscal
    -0.68
    ullah
    -0.67
    aments
    -0.65
    uli
    -0.64
    ament
    -0.62
     fitting
    -0.62
    ouf
    -0.61
     Horus
    -0.59
    ethy
    -0.59
    POSITIVE LOGITS
     forward
    1.05
     forwards
    0.96
     downhill
    0.89
     Forward
    0.79
     uphill
    0.76
     viral
    0.75
    æĸ¹
    0.74
     nowhere
    0.74
    verning
    0.73
    ãĥ£
    0.72
    Activations Density 0.056%

    No Known Activations