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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 6993
    Prev
    Next
    INDEX
    Explanations

    mentions of questions or debates regarding various topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    questions regarding the use of "whether" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Catalog
    -0.91
    Eye
    -0.82
    apt
    -0.81
    oola
    -0.80
    lator
    -0.77
    ulo
    -0.76
    unch
    -0.75
    icker
    -0.74
    ufact
    -0.72
    oxide
    -0.71
    POSITIVE LOGITS
    soever
    0.98
     there
    0.84
     anyone
    0.81
     they
    0.80
     or
    0.76
     respondents
    0.73
     anybody
    0.71
     it
    0.70
     intentional
    0.67
     he
    0.66
    Activations Density 0.044%

    No Known Activations