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. 11983
    Prev
    Next
    INDEX
    Explanations

    words indicating intensity or strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    the word "such" in high frequency 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
    ntil
    -0.84
    ertodd
    -0.75
    TeX
    -0.70
    ·
    -0.68
    iliate
    -0.68
    Ö¼
    -0.67
     Murd
    -0.67
    eanor
    -0.65
    kick
    -0.64
    achus
    -0.63
    POSITIVE LOGITS
    ities
    0.72
    ties
    0.71
    isive
    0.62
    unci
    0.61
     specificity
    0.61
    bered
    0.61
    minded
    0.61
     abundantly
    0.60
    sided
    0.60
    heartedly
    0.60
    Activations Density 0.042%

    No Known Activations