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. 8-RES-JB
    6. 4704
    Prev
    Next
    INDEX
    Explanations

    the possessive form of a person's name followed by an action or attribution

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reef
    -0.65
     override
    -0.62
     shifts
    -0.60
     Trends
    -0.59
    iency
    -0.59
     Highlights
    -0.58
    References
    -0.58
    inav
    -0.57
     Lauder
    -0.56
     Nex
    -0.56
    POSITIVE LOGITS
    been
    1.01
     gonna
    0.98
     proud
    0.89
     willing
    0.86
     been
    0.85
    ELF
    0.84
     glad
    0.82
    leeve
    0.81
     got
    0.78
    gotten
    0.77
    Activations Density 0.086%

    No Known Activations