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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 17305
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities, where one entity is rated as higher or worse than the other

    oai_token-act-pair · gpt-3.5-turbo

    comparisons to the word "other" in various contexts

    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
    oke
    -0.81
    uko
    -0.71
    ossession
    -0.67
    OA
    -0.66
    orney
    -0.64
    ony
    -0.64
     finally
    -0.64
    went
    -0.63
    enance
    -0.62
    hyde
    -0.62
    POSITIVE LOGITS
    worldly
    1.21
     kinds
    0.97
     types
    0.91
    iator
    0.84
     forms
    0.83
     incarn
    0.83
    iating
    0.83
     countries
    0.82
     facets
    0.82
     continents
    0.81
    Activations Density 0.058%

    No Known Activations