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. 16840
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of providing or seeking information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "inform" and its variations, indicating a focus on communication and information dissemination

    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
    ingu
    -0.75
    enf
    -0.62
    opes
    -0.62
    cdn
    -0.62
    oos
    -0.62
    imposed
    -0.61
    FUN
    -0.61
    cessive
    -0.61
    Pain
    -0.60
    hib
    -0.60
    POSITIVE LOGITS
    ally
    1.00
     inform
    0.87
    omic
    0.82
    acies
    0.80
     informed
    0.80
    tale
    0.75
    ulty
    0.74
    isition
    0.73
    ingly
    0.73
     incorpor
    0.73
    Activations Density 0.015%

    No Known Activations