© 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 EvalsExportsinterp-engineNEWAPI 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. 18850
    Prev
    Next
    INDEX
    Explanations

    words related to meeting specific requirements or standards

    oai_token-act-pair · gpt-3.5-turbo

    terms related to qualification and eligibility

    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
     Spice
    -0.66
     Gardens
    -0.66
    orah
    -0.65
     Lans
    -0.65
    aging
    -0.65
     Torn
    -0.64
    eland
    -0.63
     Sparrow
    -0.63
    utra
    -0.63
    stead
    -0.62
    POSITIVE LOGITS
    ifiers
    1.06
    ifications
    1.02
    ifies
    0.91
     qualifications
    0.87
    ifying
    0.86
    itatively
    0.84
    ifier
    0.82
    isites
    0.82
    animous
    0.79
     applicants
    0.78
    Activations Density 0.021%

    No Known Activations