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. 4503
    Prev
    Next
    INDEX
    Explanations

    names and terms related to various people and organizations, particularly those with the string "Ras" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or organizations, particularly with the name "Ras" or "Rasmussen"

    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
    anooga
    -0.72
    -+-+
    -0.68
    terson
    -0.68
     Hindi
    -0.66
     Lima
    -0.66
    ":[
    -0.64
    ambers
    -0.64
    ovies
    -0.63
     blo
    -0.62
    ertain
    -0.62
    POSITIVE LOGITS
    senal
    1.33
    haps
    0.89
    ussia
    0.83
    ansom
    0.80
    acing
    0.78
    uling
    0.77
    cliffe
    0.77
    ascal
    0.77
    hod
    0.74
     Racer
    0.72
    Activations Density 0.140%

    No Known Activations