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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 20925
    Prev
    Next
    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    the word "acht" and its variations, likely indicating a focus on the theme of "eight" or related concepts in a textual context

    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
    nesota
    -0.87
    ourke
    -0.81
    ãģ¦
    -0.79
     Gleaming
    -0.77
    culus
    -0.76
    ces
    -0.74
    yip
    -0.73
    gur
    -0.73
    culation
    -0.73
    ce
    -0.72
    POSITIVE LOGITS
    alion
    1.06
    rop
    0.88
    mann
    0.87
    ronics
    0.85
    ract
    0.84
    iller
    0.82
    geist
    0.80
    rieg
    0.80
    rust
    0.78
    ung
    0.77
    Activations Density 0.016%

    No Known Activations