© 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. 6-RES-JB
    11. 5489
    Prev
    Next
    INDEX
    Explanations

    names of public figures starting with the letter "T"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter 'H' or names starting with 'H'

    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
     NEC
    -0.70
     abdom
    -0.61
     Palest
    -0.60
     PubMed
    -0.58
     duct
    -0.58
     unfocusedRange
    -0.57
     capital
    -0.56
     mascara
    -0.56
     Chilean
    -0.56
     CTR
    -0.56
    POSITIVE LOGITS
    emouth
    0.85
    oshenko
    0.78
    retty
    0.77
    otta
    0.77
    udi
    0.76
    asus
    0.74
    ouk
    0.73
    asy
    0.72
    assy
    0.72
    otos
    0.72
    Activations Density 0.096%

    No Known Activations