© 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. 0-RES-JB
    11. 6609
    Prev
    Next
    INDEX
    Explanations

    information about benefits, advantages, or extra features associated with a particular item or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to benefits or advantages, particularly in the context of gaming and perks, along with mentions of vanilla-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disse
    -0.71
     Mous
    -0.70
    evidence
    -0.69
     evid
    -0.68
    examination
    -0.67
    circ
    -0.67
     extradition
    -0.67
     SEM
    -0.66
    azo
    -0.66
     Teaching
    -0.66
    POSITIVE LOGITS
     perks
    3.27
     perk
    2.98
     vanilla
    1.95
     quirks
    1.35
     quir
    1.14
     Ivy
    1.10
     Vanilla
    1.04
     unlocks
    1.02
     glitch
    0.98
     presets
    0.96
    Activations Density 0.043%

    No Known Activations