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. 17968
    Prev
    Next
    INDEX
    Explanations

    words related to hoarding or excessive accumulation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ho" and its variations, indicating a focus on expressions of enthusiasm or a certain tone

    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
     Annotations
    -0.81
     Sacrament
    -0.71
    é»Ĵ
    -0.71
     Norn
    -0.71
    âĶģ
    -0.70
     Proceedings
    -0.69
    Contract
    -0.69
    ortium
    -0.68
    ãĤ±
    -0.68
    Interstitial
    -0.67
    POSITIVE LOGITS
    arding
    1.26
    ppy
    1.07
    efully
    1.07
    eful
    1.07
    vel
    1.03
    oping
    1.00
    pper
    0.98
    ogie
    0.98
    ving
    0.96
    opy
    0.95
    Activations Density 0.005%

    No Known Activations