© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 24156
    Prev
    Next
    INDEX
    Explanations

    the word "ballpark."

    oai_token-act-pair · gpt-3.5-turbo

    references to estimates and approximations, particularly related to "ballpark" figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rique
    -0.80
    nesday
    -0.79
    amba
    -0.72
    anya
    -0.69
    OND
    -0.66
     Equality
    -0.65
     Bunny
    -0.62
     Lomb
    -0.60
     Sussex
    -0.60
    iami
    -0.59
    POSITIVE LOGITS
    geist
    0.98
     ballpark
    0.94
    dule
    0.82
    cale
    0.81
    mberg
    0.76
    objects
    0.71
    hemer
    0.70
    schild
    0.69
    iders
    0.69
    ider
    0.68
    Activations Density 0.022%

    No Known Activations