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. 7-RES-JB
    6. 4165
    Prev
    Next
    INDEX
    Explanations

    references to newspapers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newspapers and their various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayne
    -0.83
    reek
    -0.73
    orsi
    -0.72
    eri
    -0.71
    fee
    -0.71
    ensis
    -0.69
    onite
    -0.69
    roxy
    -0.69
    imus
    -0.68
     Skywalker
    -0.67
    POSITIVE LOGITS
     columnist
    0.96
     articles
    0.94
     editor
    0.90
     clipping
    0.86
     archives
    0.86
     editors
    0.85
     newspapers
    0.81
     publisher
    0.80
     advertisements
    0.79
     tabl
    0.79
    Activations Density 0.040%

    No Known Activations