© 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. 5180
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word "than"

    oai_token-act-pair · gpt-3.5-turbo

    comparisons that convey a sense of inadequacy or lack

    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
    ahime
    -0.80
    leneck
    -0.72
    ibal
    -0.70
    edia
    -0.69
    alter
    -0.67
    ModLoader
    -0.67
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.64
    olith
    -0.62
    ilon
    -0.61
    ---------
    -0.61
    POSITIVE LOGITS
     SPORTS
    0.73
    anke
    0.67
    qqa
    0.66
     Jav
    0.64
     Pik
    0.63
     Fishing
    0.58
     practicable
    0.58
     Thieves
    0.57
    catch
    0.56
    DERR
    0.55
    Activations Density 0.038%

    No Known Activations