© 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. 6725
    Prev
    Next
    INDEX
    Explanations

    specific articles or stories, possibly from news outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to news articles and stories

    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
    ibles
    -0.64
     joystick
    -0.63
    imus
    -0.62
     practise
    -0.62
     natives
    -0.61
    emonic
    -0.60
     dues
    -0.59
     fulfil
    -0.59
    arers
    -0.57
    ucer
    -0.56
    POSITIVE LOGITS
     headlined
    1.40
     titled
    1.11
     alleging
    1.07
     reporting
    1.05
     headline
    0.98
     detailing
    0.97
     published
    0.97
    article
    0.96
     article
    0.95
     exposing
    0.93
    Activations Density 0.131%

    No Known Activations