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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22410
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    technical elements related to file formats and potentially numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.65
    20439
    -0.64
     Kern
    -0.56
    gra
    -0.56
    Hart
    -0.55
     BART
    -0.55
    ©¶æ
    -0.53
     Johann
    -0.52
     Bald
    -0.52
     Messi
    -0.51
    POSITIVE LOGITS
    anwhile
    0.75
     respectively
    0.73
    %).
    0.68
    MpServer
    0.65
    lycer
    0.63
    yssey
    0.62
    ioch
    0.62
     targ
    0.61
    "/>
    0.60
    staking
    0.60
    Activations Density 0.561%

    No Known Activations