© 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
    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. 24105
    Prev
    Next
    INDEX
    Explanations

    text related to press releases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of press or news releases

    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
    acus
    -0.72
    AppData
    -0.71
    iencies
    -0.64
    alyses
    -0.63
    ometric
    -0.62
    esthetic
    -0.61
     brightest
    -0.61
    orius
    -0.60
    azes
    -0.59
    aces
    -0.59
    POSITIVE LOGITS
     announcing
    1.42
     issued
    1.23
     touting
    1.10
     detailing
    1.00
     accompanying
    1.00
     headlined
    0.95
     outlining
    0.92
     titled
    0.88
     entitled
    0.85
     confirming
    0.84
    Activations Density 0.052%

    No Known Activations