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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 23389
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news reporting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Ey," likely indicating a focus on a specific person or entity associated with the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nurture
    -0.74
    otle
    -0.72
    stall
    -0.71
     salsa
    -0.70
     master
    -0.67
    irements
    -0.64
     reset
    -0.63
     TPP
    -0.63
    release
    -0.63
     schedule
    -0.62
    POSITIVE LOGITS
     Ey
    4.15
    Ey
    2.84
     ey
    1.70
     Eye
    1.48
    Eye
    1.24
     Eyes
    1.22
     eyebrow
    1.18
     eyel
    1.14
     eyeb
    1.14
     Brow
    1.13
    Activations Density 0.019%

    No Known Activations