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. 15933
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly those with the name "Ryan"

    oai_token-act-pair · gpt-3.5-turbo

    prominent names or figures associated with 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
     Obj
    -0.82
    DATA
    -0.76
    manship
    -0.75
    HOME
    -0.75
    APH
    -0.75
    VALUE
    -0.74
    SOURCE
    -0.73
    #$#$
    -0.73
    FACE
    -0.73
    âĸ¬
    -0.71
    POSITIVE LOGITS
    monds
    0.74
    sworth
    0.69
    zens
    0.68
    iggs
    0.66
    oker
    0.65
    idan
    0.64
    uckles
    0.64
    vik
    0.63
    fill
    0.63
    utter
    0.62
    Activations Density 0.305%

    No Known Activations