Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13295
    Prev
    Next
    INDEX
    Explanations

    phrases related to hoarding behavior

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the word "ho" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Annotations
    -0.82
     Norn
    -0.75
     Sacrament
    -0.73
     GOODMAN
    -0.73
    é»Ĵ
    -0.72
     Clause
    -0.72
     Consent
    -0.68
     Proceedings
    -0.68
    ãĤ±
    -0.68
     Pyramid
    -0.68
    POSITIVE LOGITS
    arding
    1.29
    ppy
    1.14
    eful
    1.12
    vel
    1.10
    efully
    1.09
    oping
    1.08
    ogie
    1.07
    isted
    1.02
    ving
    1.01
    arded
    1.01
    Activations Density 0.006%

    No Known Activations