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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 11000
    Prev
    Next
    INDEX
    Explanations

    press releases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "press release."

    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
    AppData
    -0.75
    acus
    -0.67
     brightest
    -0.66
    audi
    -0.64
    ranch
    -0.64
     drain
    -0.63
    skill
    -0.62
    venge
    -0.61
     inheritance
    -0.61
    aces
    -0.61
    POSITIVE LOGITS
     announcing
    1.33
     issued
    1.20
     touting
    1.00
     detailing
    0.96
     titled
    0.92
     headlined
    0.88
     outlining
    0.87
     emailed
    0.86
     accompanying
    0.85
     entitled
    0.84
    Activations Density 0.029%

    No Known Activations