Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7251
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically "Les"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions or variations of the word "Schles."

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

    No Comments

    Negative Logits
    raviolet
    -0.83
     citiz
    -0.76
    ĻĤ
    -0.70
    oÄŁ
    -0.68
     carbohyd
    -0.66
     Seym
    -0.66
    tains
    -0.65
    yrinth
    -0.63
    rador
    -0.63
    condition
    -0.59
    POSITIVE LOGITS
    bury
    1.18
    bian
    1.15
    hip
    1.12
    bians
    1.11
    creen
    1.04
    pace
    1.03
    worth
    1.03
    heed
    1.02
    burg
    1.00
    mith
    0.99
    Activations Density 0.016%

    No Known Activations