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. 13686
    Prev
    Next
    INDEX
    Explanations

    words related to military or combat scenarios

    oai_token-act-pair · gpt-3.5-turbo

    the substring "ap" 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
     Monstrous
    -0.76
     phyl
    -0.73
     Masquerade
    -0.67
     interf
    -0.67
     cigars
    -0.63
    âĸ¬âĸ¬
    -0.63
    \\\\\\\\\\\\\\\\
    -0.62
     cig
    -0.62
     explan
    -0.61
     Leia
    -0.61
    POSITIVE LOGITS
    oleon
    1.29
    olitan
    1.27
    ropri
    1.21
    onent
    1.16
    ocalypse
    1.15
    ocalyptic
    1.09
    apa
    1.09
    olitics
    1.08
    osite
    1.06
    artment
    1.06
    Activations Density 0.026%

    No Known Activations