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. 21055
    Prev
    Next
    INDEX
    Explanations

    technical specifications mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specifications and statistics of devices and products

    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
    amn
    -0.73
     Wonderland
    -0.69
    nee
    -0.67
     Canal
    -0.66
    POSE
    -0.65
    ira
    -0.64
    lin
    -0.64
     istg
    -0.64
    idays
    -0.63
    legate
    -0.63
    POSITIVE LOGITS
    models
    0.89
    ynt
    0.87
    ynthesis
    0.83
     specs
    0.81
     rundown
    0.80
     metrics
    0.78
    hered
    0.76
     sheet
    0.75
    peed
    0.73
     specifications
    0.73
    Activations Density 0.118%

    No Known Activations