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. 6534
    Prev
    Next
    INDEX
    Explanations

    architectural structures or terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to architecture

    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
    lling
    -0.85
     liking
    -0.72
    ensing
    -0.69
    zzi
    -0.68
     vec
    -0.68
    TPS
    -0.68
    nder
    -0.68
    zzle
    -0.66
    cca
    -0.66
    instein
    -0.65
    POSITIVE LOGITS
    itect
    1.52
    ief
    0.98
    ocobo
    0.91
    ipel
    0.91
    opoulos
    0.91
    osaurs
    0.90
    arch
    0.84
    stadt
    0.83
    bishop
    0.80
    sylvania
    0.80
    Activations Density 0.014%

    No Known Activations