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. 12047
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a period

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of sentences that express declining to provide comments

    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
     tremend
    -1.01
     bully
    -0.92
     imagination
    -0.85
     scenery
    -0.81
     unstoppable
    -0.81
     beaut
    -0.81
     revol
    -0.81
     amazing
    -0.81
     metic
    -0.80
     gorge
    -0.80
    POSITIVE LOGITS
     Additionally
    1.35
     However
    1.25
     Previously
    1.23
    <|endoftext|>
    1.20
     Officials
    1.16
     According
    1.16
     Alternatively
    1.14
     Presumably
    1.12
     Afterwards
    1.12
     Notably
    1.11
    Activations Density 0.742%

    No Known Activations