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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 17396
    Prev
    Next
    INDEX
    Explanations

    videos labeled as "MUST WATCH" in online content

    oai_token-act-pair · gpt-3.5-turbo

    sections related to video content

    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
    Ͻ
    -0.76
     monog
    -0.66
     Andromeda
    -0.63
     Plum
    -0.62
     Gund
    -0.62
     BG
    -0.61
     altru
    -0.60
     Fortress
    -0.60
     GN
    -0.60
     Mane
    -0.59
    POSITIVE LOGITS
    Interstitial
    0.87
    Trend
    0.83
    currency
    0.75
    enezuel
    0.74
    avanaugh
    0.74
    eas
    0.74
    imedia
    0.70
     MUST
    0.70
    lect
    0.70
    tor
    0.69
    Activations Density 0.030%

    No Known Activations