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. 23444
    Prev
    Next
    INDEX
    Explanations

    website URLs for tutorials or information

    oai_token-act-pair · gpt-3.5-turbo

    links to various online resources, primarily focusing on URLs

    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
    anooga
    -0.77
     conclud
    -0.73
    ¯¯
    -0.73
    tsky
    -0.71
     srfAttach
    -0.71
    ITION
    -0.71
    ĪĴ
    -0.71
     tsun
    -0.70
     portraits
    -0.68
     grounding
    -0.68
    POSITIVE LOGITS
    debian
    1.13
    github
    1.11
    google
    1.09
    php
    1.02
    html
    1.01
    planet
    0.99
    amazon
    0.97
    facebook
    0.97
    com
    0.96
    dat
    0.94
    Activations Density 0.077%

    No Known Activations