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. 7-RES-JB
    6. 23961
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a contrast or an alternative between two possibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "or"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urated
    -0.65
    Reviewed
    -0.61
    iami
    -0.57
     Novel
    -0.56
     Barrett
    -0.56
     epile
    -0.56
    mun
    -0.54
    IDENT
    -0.54
     Ambro
    -0.54
    birth
    -0.54
    POSITIVE LOGITS
    Else
    1.18
    nery
    1.11
    acles
    1.09
    lando
    1.09
    nam
    1.04
    acular
    1.01
    chard
    0.99
    acle
    0.97
     else
    0.88
    lez
    0.84
    Activations Density 0.078%

    No Known Activations