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. 7-RES-JB
    6. 19946
    Prev
    Next
    INDEX
    Explanations

    words related to comparisons and attributes in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" to denote existence or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urry
    -0.74
    ear
    -0.70
    inav
    -0.67
    itri
    -0.65
    results
    -0.63
    alin
    -0.62
    uld
    -0.60
     muster
    -0.59
    PsyNetMessage
    -0.58
     override
    -0.58
    POSITIVE LOGITS
     supposed
    1.04
     definitely
    1.03
    nt
    0.99
     adamant
    0.99
     currently
    0.95
     indeed
    0.94
     proud
    0.93
     certainly
    0.92
     not
    0.92
     unlikely
    0.91
    Activations Density 0.343%

    No Known Activations