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. 15500
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical values, particularly related to changes or distributions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a transition or a goal, particularly with the word "to" followed by various objectives or changes

    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
    alogy
    -0.69
     mosa
    -0.68
    ergic
    -0.67
    vo
    -0.66
    nostic
    -0.66
    fol
    -0.65
    cffffcc
    -0.63
    iHUD
    -0.63
    nexus
    -0.63
    hemat
    -0.61
    POSITIVE LOGITS
    pload
    0.99
     compensate
    0.95
     expel
    0.92
     commemorate
    0.91
     celebrate
    0.86
     conserve
    0.84
    pless
    0.83
     abolish
    0.81
     eliminate
    0.80
     accommodate
    0.80
    Activations Density 0.134%

    No Known Activations