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. 11-RES-JB
    6. 15460
    Prev
    Next
    INDEX
    Explanations

    names of news outlets in the text

    oai_token-act-pair · gpt-3.5-turbo

    news outlet names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    figure
    -0.74
    }}}
    -0.70
     obser
    -0.65
    Interstitial
    -0.63
    gradient
    -0.62
    emort
    -0.61
    taboola
    -0.60
     vulner
    -0.60
    cffffcc
    -0.59
    fig
    -0.57
    POSITIVE LOGITS
     that
    1.08
    that
    0.92
     he
    0.84
     they
    0.84
     there
    0.76
     she
    0.75
    è¦ļéĨĴ
    0.73
     it
    0.69
     THAT
    0.67
     yesterday
    0.65
    Activations Density 0.106%

    No Known Activations