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. 10517
    Prev
    Next
    INDEX
    Explanations

    words related to solving difficult problems or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ol" and its variations in different contexts

    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
     Battles
    -0.70
     ISS
    -0.68
    éĹ
    -0.67
     Healer
    -0.66
     UFO
    -0.65
     Presidential
    -0.65
    DATA
    -0.65
     Citizen
    -0.65
    ãģ®éŃĶ
    -0.65
    æĿ
    -0.65
    POSITIVE LOGITS
    ipop
    1.25
    ateral
    1.19
    onial
    1.12
    ength
    1.06
    ounge
    1.03
    ivia
    1.02
    oad
    1.01
    adies
    1.01
    okia
    1.00
    phe
    0.97
    Activations Density 0.019%

    No Known Activations