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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 13420
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a connection, comparison, or alternation

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases expressing possibility or likelihood

    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
     Pony
    -0.89
     Cth
    -0.88
     mummy
    -0.65
     pandemonium
    -0.61
     Steel
    -0.60
     Centauri
    -0.60
     Rocket
    -0.60
     Columb
    -0.59
     Chow
    -0.58
     Rainbow
    -0.58
    POSITIVE LOGITS
    acles
    1.38
    acular
    1.26
    chard
    1.25
    acle
    1.24
    leans
    1.15
    GAN
    1.15
    chid
    1.12
    Else
    1.10
    nery
    1.08
    lando
    1.02
    Activations Density 0.074%

    No Known Activations