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. 12286
    Prev
    Next
    INDEX
    Explanations

    words or phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that are cited or quoted, often marked by quotation marks

    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
     pse
    -0.78
     tremend
    -0.77
     hooks
    -0.76
     throne
    -0.75
     destro
    -0.75
     hatch
    -0.74
     refunds
    -0.72
     rall
    -0.71
     reside
    -0.69
     vents
    -0.68
    POSITIVE LOGITS
    false
    1.13
    true
    1.09
    pure
    1.04
    mega
    1.03
    smart
    1.02
    Operation
    1.01
    prem
    1.00
    cal
    0.99
    personal
    0.99
    ordinary
    0.97
    Activations Density 0.071%

    No Known Activations