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. 1984
    Prev
    Next
    INDEX
    Explanations

    mentions of actions involving the nose

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "sn" likely referring to derogatory or negative slang terms

    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
    heid
    -0.84
    xual
    -0.72
    EMENT
    -0.72
    WAYS
    -0.65
    shire
    -0.64
     PowerPoint
    -0.61
    minus
    -0.61
     lack
    -0.61
    mine
    -0.61
     Templar
    -0.58
    POSITIVE LOGITS
    obb
    1.17
    appers
    1.15
    agging
    1.15
    atching
    1.15
    agged
    1.14
    apper
    1.13
    atches
    1.12
    appy
    1.10
    oot
    1.09
    ips
    1.09
    Activations Density 0.012%

    No Known Activations