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. 3-RES-JB
    6. 22454
    Prev
    Next
    INDEX
    Explanations

    the letter "B" followed by a single digit number

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'B'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.84
    oldemort
    -0.67
     dere
    -0.65
     por
    -0.64
     Voldemort
    -0.62
     Militia
    -0.61
     Lerner
    -0.61
    espie
    -0.60
    terday
    -0.60
     Pharaoh
    -0.59
    POSITIVE LOGITS
    aked
    1.07
    rug
    1.07
    rows
    1.04
    razen
    1.04
    rief
    1.03
    urt
    1.03
    odies
    1.01
    anc
    1.00
    abb
    1.00
    uch
    0.99
    Activations Density 0.054%

    No Known Activations