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. 2308
    Prev
    Next
    INDEX
    Explanations

    the word "the" occurring at the end of the sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" occurring frequently in various contexts

    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
    ibaba
    -0.77
    amsung
    -0.70
    abi
    -0.69
    pport
    -0.69
     solves
    -0.68
    orea
    -0.67
     âĢº
    -0.62
    iatrics
    -0.61
    etsk
    -0.61
     reside
    -0.61
    POSITIVE LOGITS
     same
    0.97
     sheer
    0.87
     aforementioned
    0.87
     widest
    0.87
     end
    0.86
     outset
    0.85
     margins
    0.84
     usual
    0.84
     slightest
    0.81
    ses
    0.80
    Activations Density 0.119%

    No Known Activations