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. 12-RES-JB
    6. 14662
    Prev
    Next
    INDEX
    Explanations

    quotations spoken by individuals, particularly in news reports or press conferences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances related to the presence of reporters or journalists discussing topics in a press setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.90
    UTH
    -0.84
     conflic
    -0.78
    à¨
    -0.73
    WithNo
    -0.73
     Defin
    -0.72
    ĵ
    -0.69
    Fight
    -0.69
    ĪĴ
    -0.68
    AE
    -0.67
    POSITIVE LOGITS
     aboard
    1.18
     afterward
    1.14
     gathered
    1.10
     assembled
    1.01
     afterwards
    0.98
     outside
    0.96
     backstage
    0.94
     stationed
    0.94
     traveling
    0.93
     ahead
    0.90
    Activations Density 0.052%

    No Known Activations