© 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. 7102
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and corporate actions, particularly involving stock buyouts and sales

    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
     Monstrous
    -0.70
    urous
    -0.66
     constitu
    -0.64
    orically
    -0.62
     Curious
    -0.61
     Aven
    -0.60
     Heights
    -0.59
     Genius
    -0.59
     spirits
    -0.58
    ciating
    -0.58
    POSITIVE LOGITS
    outs
    1.53
    out
    1.49
    ups
    1.43
    up
    1.43
    offs
    1.38
    backs
    1.36
    back
    1.35
    downs
    1.34
    down
    1.34
    off
    1.33
    Activations Density 0.215%

    No Known Activations