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. 7-RES-JB
    6. 4456
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "as you can see."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "you can see."

    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
    ortunately
    -0.68
    wake
    -0.63
    nation
    -0.62
     reven
    -0.62
    cycl
    -0.61
    asca
    -0.61
    raid
    -0.60
    inqu
    -0.59
    ophone
    -0.58
    sters
    -0.58
    POSITIVE LOGITS
     why
    0.84
     whats
    0.81
     clearly
    0.80
     how
    0.77
     glimps
    0.77
     plainly
    0.77
     outlines
    0.71
    ById
    0.70
    seeing
    0.70
    point
    0.69
    Activations Density 0.067%

    No Known Activations