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. 6894
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming or software development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the game "Mabinogi."

    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
    apixel
    -0.76
    pel
    -0.70
    mie
    -0.68
    anny
    -0.67
    forts
    -0.66
    plement
    -0.66
    aditional
    -0.65
    plets
    -0.64
    igible
    -0.64
    esome
    -0.64
    POSITIVE LOGITS
    jamin
    0.96
    ãĥĥãĥī
    0.90
    Bay
    0.85
    osta
    0.81
    heimer
    0.77
    Reward
    0.75
    Bah
    0.74
    owitz
    0.72
    Journal
    0.69
    Ke
    0.69
    Activations Density 0.019%

    No Known Activations