© 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. 10-RES-JB
    11. 14115
    Prev
    Next
    INDEX
    Explanations

    companies and startups taking advantage of opportunities or trends in their respective industries

    oai_token-act-pair · gpt-3.5-turbo

    references to technology companies and their strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deen
    -0.70
    Person
    -0.69
    juries
    -0.67
     Documents
    -0.67
     Okawaru
    -0.66
    ultimate
    -0.63
    maximum
    -0.63
     Heard
    -0.62
     JUSTICE
    -0.62
     Morty
    -0.61
    POSITIVE LOGITS
     vying
    1.20
     experimenting
    1.16
     experimented
    1.07
     innov
    1.02
     sprung
    1.01
     endeav
    1.01
     embracing
    1.00
     incorporating
    1.00
     touting
    0.99
     employing
    0.98
    Activations Density 0.349%

    No Known Activations