Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 24095
    Prev
    Next
    INDEX
    Explanations

    instances of the word "right" in close proximity to prepositions or other contextual cues

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating physical presence or location in time and space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iple
    -0.78
    vari
    -0.73
    orously
    -0.70
    iatric
    -0.70
    ply
    -0.70
    marine
    -0.68
    amar
    -0.68
    uscript
    -0.68
    imens
    -0.67
    ravel
    -0.67
    POSITIVE LOGITS
     doorstep
    0.67
     Shooter
    0.65
    enegger
    0.63
     Wrong
    0.63
    edge
    0.60
     Stockholm
    0.59
     Bolt
    0.59
     Guns
    0.58
     Hog
    0.58
     Centre
    0.58
    Activations Density 0.077%

    No Known Activations