© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17356
    Prev
    Next
    INDEX
    Explanations

    references to the word "col" which could be a shortened form of "color" or have some other contextual meaning

    oai_token-act-pair · gpt-3.5-turbo

    references to the color "colon"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.76
    natureconservancy
    -0.74
    wered
    -0.69
    isSpecialOrderable
    -0.68
    ELF
    -0.67
     forth
    -0.66
    shapeshifter
    -0.65
    butt
    -0.64
    ARP
    -0.64
    CVE
    -0.63
    POSITIVE LOGITS
    onel
    1.22
    ossal
    1.10
    lections
    1.05
    onial
    1.04
    ouri
    0.99
    ombo
    0.98
    oured
    0.96
    ouring
    0.96
    umbo
    0.95
    ossus
    0.95
    Activations Density 0.010%

    No Known Activations