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. 8-RES-JB
    6. 5785
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Bronco"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Bronco," likely relating to the vehicle or the sports team

    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
    ENC
    -0.76
     srfAttach
    -0.71
    nikov
    -0.71
    Variable
    -0.67
    variable
    -0.66
    ACTION
    -0.65
     ILCS
    -0.64
    Ocean
    -0.64
    ional
    -0.63
    enced
    -0.62
    POSITIVE LOGITS
    fman
    0.98
    bsite
    0.92
    zeb
    0.90
    etooth
    0.88
    zes
    0.88
    zos
    0.88
    cies
    0.86
    swer
    0.85
    hm
    0.83
    sonian
    0.82
    Activations Density 0.065%

    No Known Activations