© 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. 16669
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Rec" followed by a specific number indicating a record or an abbreviation for "Recommendation"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Rec" in various contexts

    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
    furt
    -0.79
    MENTS
    -0.74
    ahime
    -0.70
    tips
    -0.66
     Tasman
    -0.65
     Kenyan
    -0.65
    OPLE
    -0.65
    Magikarp
    -0.65
    MENT
    -0.61
    loo
    -0.61
    POSITIVE LOGITS
    ycle
    1.19
    urrent
    1.12
    oded
    1.12
    ipient
    1.08
    ipes
    1.05
    ruit
    1.04
    ursive
    1.01
    ruits
    1.01
    onduct
    0.94
    ursion
    0.92
    Activations Density 0.007%

    No Known Activations