© 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. 7-RES-JB
    11. 20728
    Prev
    Next
    INDEX
    Explanations

    terms related to business and organizational management

    oai_token-act-pair · gpt-3.5-turbo

    references to management concepts and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -1.14
    DonaldTrump
    -0.84
    lihood
    -0.75
    ead
    -0.73
    ym
    -0.71
    ENC
    -0.70
    bley
    -0.69
    ibli
    -0.69
    tein
    -0.68
    olic
    -0.66
    POSITIVE LOGITS
    eers
    0.83
     consultancy
    0.82
    eering
    0.82
     strategies
    0.79
    ahime
    0.76
    eer
    0.74
     controls
    0.73
     suites
    0.73
     oversight
    0.72
     strategy
    0.72
    Activations Density 0.029%

    No Known Activations