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. 6-RES-JB
    6. 1803
    Prev
    Next
    INDEX
    Explanations

    words related to black boxes or controversial items marked by the term "black"

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with "black box" concepts and events, particularly related to warning signs and markets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osw
    -0.86
    fam
    -0.69
    udeb
    -0.65
    _-
    -0.63
     Living
    -0.61
    BIL
    -0.61
    bare
    -0.61
    leave
    -0.61
    verified
    -0.61
    upper
    -0.61
    POSITIVE LOGITS
    eers
    1.03
     Reloaded
    0.83
     Initiative
    0.69
     ®
    0.68
    eering
    0.68
    izons
    0.67
     Strategy
    0.64
     superpower
    0.64
     Sachs
    0.63
     civilisation
    0.62
    Activations Density 0.130%

    No Known Activations