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. 10090
    Prev
    Next
    INDEX
    Explanations

    words related to tectonic plates and geological processes

    oai_token-act-pair · gpt-3.5-turbo

    words related to geological and physical sciences, particularly those ending in 'onic'

    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
    een
    -0.87
    ful
    -0.85
    ded
    -0.83
    ding
    -0.83
    suit
    -0.81
    fully
    -0.80
    adr
    -0.80
    Tex
    -0.77
    eer
    -0.74
    matched
    -0.74
    POSITIVE LOGITS
     acid
    0.90
     arsen
    0.85
    olor
    0.81
     plague
    0.78
    osis
    0.76
    ãĥ³ãĤ¸
    0.74
     submer
    0.71
     pent
    0.70
    scill
    0.70
    otin
    0.68
    Activations Density 0.022%

    No Known Activations