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. 705
    Prev
    Next
    INDEX
    Explanations

    foreign characters or character combinations in the text

    oai_token-act-pair · gpt-3.5-turbo

    special characters and strings of text in various encodings

    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
    reau
    -0.97
    issance
    -0.60
    steen
    -0.59
    ruary
    -0.58
    odder
    -0.57
    olicy
    -0.56
     sidx
    -0.56
    imately
    -0.55
     blindly
    -0.54
     nowadays
    -0.53
    POSITIVE LOGITS
    zbek
    0.67
    ģ«
    0.65
    llah
    0.64
    uko
    0.60
     amen
    0.60
    rontal
    0.60
     guiActiveUnfocused
    0.60
    ForgeModLoader
    0.59
    esm
    0.58
    lander
    0.58
    Activations Density 1.112%

    No Known Activations