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. 1-RES-JB
    6. 4035
    Prev
    Next
    INDEX
    Explanations

    the name "Bull" followed by a number, potentially referencing a person or a brand

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Bull" associated with various contexts or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¦
    -0.75
    UTC
    -0.71
    LEASE
    -0.71
    ULAR
    -0.69
    LY
    -0.68
    Interstitial
    -0.68
    lihood
    -0.67
    ONS
    -0.66
    TERN
    -0.66
    liness
    -0.66
    POSITIVE LOGITS
     Bull
    1.09
    shit
    0.96
     Bulls
    0.89
    keye
    0.89
    aroo
    0.87
    iac
    0.84
    iatus
    0.83
    iard
    0.83
    Bull
    0.82
    gart
    0.80
    Activations Density 0.009%

    No Known Activations