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. 10-RES-JB
    6. 15110
    Prev
    Next
    INDEX
    Explanations

    links or references to externally hosted content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of square brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transported
    -0.74
     converted
    -0.73
     poisoning
    -0.72
     uncertain
    -0.71
     swe
    -0.70
    isers
    -0.67
     handed
    -0.67
     intellig
    -0.66
     cones
    -0.65
     equivalents
    -0.65
    POSITIVE LOGITS
    â̦]
    1.52
    ...]
    1.50
    youtube
    1.29
    np
    1.27
    UPDATE
    1.24
    EDIT
    1.24
    Laughs
    1.23
    img
    1.22
    email
    1.20
    Update
    1.20
    Activations Density 0.031%

    No Known Activations