© 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. 11-RES-JB
    11. 7115
    Prev
    Next
    INDEX
    Explanations

    mentions of clients in business contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itialized
    -0.74
     Haram
    -0.71
    lihood
    -0.65
     guts
    -0.62
     Pole
    -0.60
     Maw
    -0.59
     Prev
    -0.59
     AMERICA
    -0.58
    ansk
    -0.57
    displayText
    -0.56
    POSITIVE LOGITS
    ele
    1.78
    elist
    1.03
    client
    0.84
    Rect
    0.81
    Hello
    0.80
    roach
    0.79
    ulent
    0.78
    hetically
    0.77
    hire
    0.74
    el
    0.74
    Activations Density 0.028%

    No Known Activations