© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 15397
    Prev
    Next
    INDEX
    Explanations

    mentions or references to conferences or events

    oai_token-act-pair · gpt-3.5-turbo

    references to conventions, especially in terms of their locations and associated events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -0.92
    tera
    -0.75
    cam
    -0.72
    arma
    -0.65
    iless
    -0.64
    obi
    -0.63
    ï¸ı
    -0.62
    wx
    -0.62
    roxy
    -0.62
    azo
    -0.61
    POSITIVE LOGITS
    eers
    1.39
    ally
    0.97
    eer
    0.96
    eering
    0.92
     convention
    0.90
     Convention
    0.88
    ality
    0.87
     delegates
    0.82
    naire
    0.81
    izzle
    0.80
    Activations Density 0.036%

    No Known Activations