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. 10220
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, specifically mentioning Apache software

    oai_token-act-pair · gpt-3.5-turbo

    references to the Apache software or related terminology

    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
    burse
    -0.70
    icle
    -0.68
    enegger
    -0.67
    rier
    -0.67
    haar
    -0.66
    urst
    -0.66
    clock
    -0.65
    telling
    -0.65
     Madden
    -0.65
    iard
    -0.64
    POSITIVE LOGITS
     Apache
    0.92
     multic
    0.70
     Commons
    0.67
    enhagen
    0.66
    ress
    0.66
     HTTP
    0.65
    Ap
    0.65
    apache
    0.64
    anth
    0.63
    ĺħ
    0.63
    Activations Density 0.012%

    No Known Activations