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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17590
    Prev
    Next
    INDEX
    Explanations

    mentions of statements or quotes made by people to reporters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reporters."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTH
    -0.69
    youtube
    -0.64
    osate
    -0.64
    alys
    -0.60
     tyrann
    -0.60
    xe
    -0.59
    emonic
    -0.59
    gradation
    -0.56
    ez
    -0.56
    rome
    -0.56
    POSITIVE LOGITS
     gathered
    1.03
     aboard
    1.01
     assembled
    0.93
     afterward
    0.92
     backstage
    0.90
     stationed
    0.90
    hips
    0.87
     traveling
    0.83
     Wednesday
    0.81
     reporters
    0.80
    Activations Density 0.052%

    No Known Activations