Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 2096
    Prev
    Next
    INDEX
    Explanations

    references to press conferences

    oai_token-act-pair · gpt-3.5-turbo

    references to press conferences or statements made to the media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.80
    *=-
    -0.69
    abama
    -0.67
     Bram
    -0.67
    inho
    -0.66
    ston
    -0.64
     Sponge
    -0.64
     Parenthood
    -0.61
    irst
    -0.60
     Valhalla
    -0.59
    POSITIVE LOGITS
    urized
    0.96
    press
    0.93
     conference
    0.91
    conference
    0.85
    wire
    0.84
     corps
    0.83
     conferences
    0.83
     press
    0.80
     Coverage
    0.78
     aggregation
    0.78
    Activations Density 0.022%

    No Known Activations