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. 4-RES-JB
    6. 5156
    Prev
    Next
    INDEX
    Explanations

    dates or references to historical or religious events

    oai_token-act-pair · gpt-3.5-turbo

    references to episodes or segments in a series

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

    No Comments

    Negative Logits
    FUL
    -0.98
    LESS
    -0.87
    veyard
    -0.73
    ^^^^
    -0.72
     Pru
    -0.72
    ARDS
    -0.70
    hips
    -0.69
    WAYS
    -0.69
    âĺĨ
    -0.69
    ''''
    -0.69
    POSITIVE LOGITS
    iphany
    1.35
    iscopal
    1.23
    istle
    1.21
    hemer
    1.18
    isodes
    1.12
    onymous
    1.01
    iph
    1.00
    igen
    0.99
    isc
    0.98
    oton
    0.97
    Activations Density 0.012%

    No Known Activations