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. 23
    Prev
    Next
    INDEX
    Explanations

    phrases indicating complete exclusion or abandonment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "altogether."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    altogether

    np_max-act-logits · claude-3-5-haiku-20241022Triggered by @johnny
    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
    hao
    -0.69
     Patriarch
    -0.65
    yer
    -0.65
    hma
    -0.64
    yers
    -0.63
    enf
    -0.61
     Apache
    -0.60
     Fulton
    -0.60
    essed
    -0.60
     Cascade
    -0.59
    POSITIVE LOGITS
     disarm
    0.74
     ç¥ŀ
    0.73
     guiActiveUn
    0.71
    loo
    0.69
    ICA
    0.69
    gebra
    0.64
     Cors
    0.64
    ADRA
    0.63
    EngineDebug
    0.63
    IONS
    0.63
    Activations Density 0.010%

    No Known Activations