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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5241
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and science

    oai_token-act-pair · gpt-3.5-turbo

    specific names or titles of entities, particularly relating to awards, missions, or features in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .''.
    -0.63
    hesive
    -0.62
    ril
    -0.62
    .).
    -0.57
    ————————————————
    -0.57
    )).
    -0.55
    usercontent
    -0.55
    .�
    -0.54
    anchester
    -0.54
    ãĤ¤ãĥĪ
    -0.53
    POSITIVE LOGITS
     meanwhile
    0.76
     analogy
    0.73
    speak
    0.71
     nutshell
    0.69
     however
    0.65
     jargon
    0.65
     example
    0.63
    imester
    0.63
    pedia
    0.62
    peak
    0.61
    Activations Density 0.770%

    No Known Activations