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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 8082
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "Because of this,"

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases, particularly those introducing ideas or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    staking
    -0.77
    arov
    -0.71
    onym
    -0.70
    gow
    -0.67
    Optional
    -0.62
    Uk
    -0.61
    ania
    -0.59
    assed
    -0.58
    Bee
    -0.58
    NBA
    -0.57
    POSITIVE LOGITS
     however
    0.88
    SPONSORED
    0.79
     we
    0.79
     alas
    0.77
     moreover
    0.72
     please
    0.71
    isen
    0.65
     let
    0.65
     mathemat
    0.63
     whenever
    0.62
    Activations Density 0.199%

    No Known Activations