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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 4334
    Prev
    Next
    INDEX
    Explanations

    mentions of physical injuries or dislocations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dislocation" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     til
    -0.84
     tilt
    -0.80
    forward
    -0.70
     ][
    -0.65
     Hof
    -0.63
     Feinstein
    -0.62
    scan
    -0.62
     Apex
    -0.61
    iator
    -0.61
    focus
    -0.61
    POSITIVE LOGITS
     disl
    3.33
     dislike
    1.02
    article
    0.93
    tre
    0.92
     disliked
    0.91
    tale
    0.91
     oppos
    0.89
     Yellow
    0.89
     pir
    0.83
     misses
    0.82
    Activations Density 0.021%

    No Known Activations