© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 22603
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning "The Hollywood Reporter."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific reporters and reporting entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rams
    -0.91
    sur
    -0.82
    inst
    -0.80
    err
    -0.78
    chat
    -0.73
    rals
    -0.72
    sky
    -0.72
    BuyableInstoreAndOnline
    -0.71
    reek
    -0.70
    gone
    -0.70
    POSITIVE LOGITS
     Reporter
    1.43
     Examiner
    0.92
     Journalists
    0.90
     Worker
    0.84
     Investor
    0.82
     Transcript
    0.77
     Writer
    0.77
     Weekly
    0.76
     Digest
    0.74
     Photographer
    0.73
    Activations Density 0.006%

    No Known Activations