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. 15162
    Prev
    Next
    INDEX
    Explanations

    **mentions of the basketball player Goran Dragic**

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gor" or related terms

    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
    terday
    -0.82
    WAYS
    -0.75
     sett
    -0.72
    INESS
    -0.68
     PATH
    -0.65
     Fargo
    -0.65
     MacArthur
    -0.64
     Settlement
    -0.64
     Hath
    -0.63
     quo
    -0.63
    POSITIVE LOGITS
    izont
    1.20
    achev
    1.11
    andum
    0.96
    oshenko
    0.96
    ongyang
    0.93
    Äį
    0.93
    aband
    0.91
    izontal
    0.90
    oz
    0.89
    ringe
    0.89
    Activations Density 0.044%

    No Known Activations