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. 8206
    Prev
    Next
    INDEX
    Explanations

    the pattern "X" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the token 'X' in various 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
    getic
    -0.84
    kson
    -0.79
    enegger
    -0.70
    inally
    -0.69
    ufact
    -0.68
     captcha
    -0.66
    ¢
    -0.66
    cffff
    -0.66
    Ú
    -0.65
     Poké
    -0.64
    POSITIVE LOGITS
    avier
    1.28
    peria
    1.21
    cellence
    1.14
    posed
    0.96
    aminer
    0.96
    III
    0.94
    odus
    0.92
    clusive
    0.92
    posure
    0.92
    ML
    0.92
    Activations Density 0.027%

    No Known Activations