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. 20231
    Prev
    Next
    INDEX
    Explanations

    terms related to technology companies and projects

    oai_token-act-pair · gpt-3.5-turbo

    language related to charitable contributions and nonprofit organizations

    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
    lying
    -0.68
    schild
    -0.64
    DonaldTrump
    -0.60
    alions
    -0.58
     corros
    -0.58
     )]
    -0.56
    isky
    -0.56
    mbudsman
    -0.56
    cli
    -0.56
    threat
    -0.56
    POSITIVE LOGITS
     Comic
    0.71
     Anime
    0.65
     somew
    0.65
     themed
    0.65
     sci
    0.63
     Robot
    0.63
     backstage
    0.61
     shutter
    0.61
    Gamer
    0.60
     Nebula
    0.60
    Activations Density 1.855%

    No Known Activations