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. 17734
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and software development, particularly involving function support and programming instances

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns and keywords related to various topics or entities

    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
    ],"
    -0.72
    interstitial
    -0.61
    PsyNetMessage
    -0.58
    achelor
    -0.55
     captcha
    -0.55
    )",
    -0.54
     bothering
    -0.54
     mouth
    -0.53
     disguise
    -0.53
    itbart
    -0.53
    POSITIVE LOGITS
     meanwhile
    0.79
     however
    0.75
    beit
    0.74
     ---------
    0.70
    vic
    0.70
    sequently
    0.69
    ogether
    0.69
    udos
    0.66
    hetically
    0.66
     refers
    0.65
    Activations Density 0.842%

    No Known Activations