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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 6672
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "Not all" highlighting exceptions or variations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "not all," indicating exceptions or counterexamples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOT
    -0.73
    ternal
    -0.72
    =#
    -0.65
    not
    -0.64
    minster
    -0.63
    oided
    -0.63
     SetTextColor
    -0.63
    oru
    -0.62
    Numbers
    -0.61
    LEASE
    -0.60
    POSITIVE LOGITS
     anymore
    1.18
     nor
    1.04
     necessarily
    0.76
     anyone
    0.74
     anybody
    0.74
     slightest
    0.71
     yet
    0.69
    ody
    0.68
     gays
    0.67
     whatsoever
    0.66
    Activations Density 0.038%

    No Known Activations