© 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. 1-RES-JB
    11. 16418
    Prev
    Next
    INDEX
    Explanations

    adverbs that express a preference or choice

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rather"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DD
    -0.77
    amba
    -0.74
    anon
    -0.72
    ORN
    -0.72
    haw
    -0.69
    ppo
    -0.67
    onga
    -0.66
    mberg
    -0.66
    ongo
    -0.65
    ipl
    -0.64
    POSITIVE LOGITS
     rather
    0.82
     Ide
    0.75
     unpop
    0.74
    rather
    0.72
    bilt
    0.71
    itably
    0.70
     unimagin
    0.69
     metic
    0.67
     Neh
    0.66
     than
    0.66
    Activations Density 0.015%

    No Known Activations