Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 12686
    Prev
    Next
    INDEX
    Explanations

    phrases related to a process of certification, often involving reconsideration, or repetition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rec" in various forms related to recognition and reporting

    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
    MENTS
    -0.78
    loo
    -0.77
    furt
    -0.72
    nuts
    -0.72
    )=(
    -0.71
    NESS
    -0.70
     Masters
    -0.70
     Gemini
    -0.69
    MENT
    -0.69
    bags
    -0.69
    POSITIVE LOGITS
    ourses
    1.08
    ievers
    1.05
    ursion
    1.04
    onduct
    1.03
    uters
    1.03
    occ
    1.03
    urrence
    1.02
    ategor
    1.01
    secut
    1.01
    oding
    0.99
    Activations Density 0.008%

    No Known Activations