© 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. 3-RES-JB
    11. 18098
    Prev
    Next
    INDEX
    Explanations

    words related to specific food items or descriptors like "organic" and "quality."

    oai_token-act-pair · gpt-3.5-turbo

    plural noun forms and suffix variations

    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
    CHAR
    -0.70
    GAN
    -0.67
     Feder
    -0.63
     VID
    -0.62
     MOD
    -0.61
     Atom
    -0.61
    Reviewer
    -0.59
    ãĥĥ
    -0.59
    SW
    -0.58
    ITNESS
    -0.57
    POSITIVE LOGITS
    hips
    1.29
    hare
    1.28
    mith
    1.24
    hops
    1.15
    poons
    1.15
    ilver
    1.13
    hell
    1.13
    poon
    1.08
    heet
    1.07
    etting
    1.06
    Activations Density 0.184%

    No Known Activations