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. 11963
    Prev
    Next
    INDEX
    Explanations

    mentions of the adjective "mild" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mild" and its variations

    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
    berus
    -0.73
    andise
    -0.69
     Blackwell
    -0.68
    alogue
    -0.68
    ynthesis
    -0.68
    ilater
    -0.66
     Chase
    -0.65
    ÃįÃį
    -0.65
     Dame
    -0.64
     Framework
    -0.64
    POSITIVE LOGITS
    er
    1.18
    est
    1.10
    ew
    1.05
    ers
    0.98
    erate
    0.96
    ener
    0.92
    ening
    0.91
    ering
    0.86
    ened
    0.85
    ens
    0.81
    Activations Density 0.014%

    No Known Activations