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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 12098
    Prev
    Next
    INDEX
    Explanations

    references to communication attempts or responses

    oai_token-act-pair · gpt-3.5-turbo

    references to requests for comments or responses from individuals or organizations

    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
    sed
    -0.73
    orsche
    -0.71
    edes
    -0.68
     joints
    -0.66
     bonding
    -0.64
    erva
    -0.64
    unts
    -0.63
    steen
    -0.61
     commanding
    -0.61
     valves
    -0.61
    POSITIVE LOGITS
     Coverage
    1.06
     reporter
    0.88
     Editorial
    0.86
     interview
    0.84
     reporters
    0.83
     editorial
    0.83
     coverage
    0.82
     Inqu
    0.82
     Newsp
    0.82
     contacted
    0.81
    Activations Density 0.700%

    No Known Activations