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. 1303
    Prev
    Next
    INDEX
    Explanations

    words/phrases related to negation or refutation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the contraction "don't"

    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
     tremend
    -0.83
     behavi
    -0.76
    ħĭ
    -0.74
    Reviewer
    -0.74
     Skydragon
    -0.74
    ĪĴ
    -0.72
     hemor
    -0.70
    Ĥİ
    -0.66
    £ı
    -0.64
     dust
    -0.63
    POSITIVE LOGITS
    otally
    1.11
    ween
    1.06
    cha
    0.93
    urtle
    0.93
    ruck
    0.93
    uple
    0.93
    aper
    0.90
    ional
    0.90
    itles
    0.90
    aylor
    0.89
    Activations Density 0.118%

    No Known Activations