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. 10-RES-JB
    6. 9081
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their creative works or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endment
    -0.84
    hari
    -0.82
    Invalid
    -0.80
    izabeth
    -0.74
    ovo
    -0.74
    loader
    -0.74
    Error
    -0.74
    isance
    -0.73
    jury
    -0.72
    needed
    -0.72
    POSITIVE LOGITS
     creations
    1.47
     compositions
    1.38
     productions
    1.28
     talents
    1.19
     masterpiece
    1.17
     repertoire
    1.15
     accomplishments
    1.13
     signature
    1.13
     newest
    1.12
     writings
    1.12
    Activations Density 0.255%

    No Known Activations