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. 8-RES-JB
    6. 1434
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing dissatisfaction and disagreement with others

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or clauses that express ongoing actions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uto
    -0.67
    ¬¼
    -0.60
    ophon
    -0.58
    ague
    -0.58
    irie
    -0.56
    atari
    -0.56
    iculty
    -0.56
    ase
    -0.55
    Forge
    -0.55
     DevOnline
    -0.55
    POSITIVE LOGITS
     huh
    1.25
     ..."
    1.13
     eh
    1.13
     sir
    1.07
    ]"
    1.01
     namely
    0.95
     haha
    0.94
    \"
    0.93
    [/
    0.91
    ,''
    0.90
    Activations Density 0.301%

    No Known Activations