© 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. 8-RES-JB
    11. 4108
    Prev
    Next
    INDEX
    Explanations

    verbs denoting actions or tasks being done

    oai_token-act-pair · gpt-3.5-turbo

    the word "doing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sg
    -0.75
    lights
    -0.74
    wit
    -0.66
    UTH
    -0.64
     Secondly
    -0.63
    liner
    -0.61
    uses
    -0.61
    mares
    -0.61
    Tier
    -0.61
    pter
    -0.61
    POSITIVE LOGITS
     brisk
    0.85
     laundry
    0.84
     nothing
    0.81
     alright
    0.73
     err
    0.72
    pez
    0.71
    omsday
    0.71
     poorly
    0.71
     homework
    0.70
    berman
    0.70
    Activations Density 0.071%

    No Known Activations