© 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. 11074
    Prev
    Next
    INDEX
    Explanations

    text related to software systems and technologies

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence closures in a text

    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
    ascus
    -0.82
     carbohyd
    -0.80
     earthqu
    -0.79
     gobl
    -0.76
     spor
    -0.75
    ikuman
    -0.74
    lled
    -0.74
     satell
    -0.71
     boarded
    -0.71
     teasp
    -0.70
    POSITIVE LOGITS
     Additionally
    1.54
     Furthermore
    1.44
     Moreover
    1.43
     Conversely
    1.39
     Alternatively
    1.35
     Similarly
    1.35
     Lastly
    1.34
     Likewise
    1.33
     Also
    1.28
     Plus
    1.26
    Activations Density 0.436%

    No Known Activations