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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 7634
    Prev
    Next
    INDEX
    Explanations

    phrases related to features or qualities of products or services

    oai_token-act-pair · gpt-3.5-turbo

    economic and operational terms related to a nation's strength and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.81
    agen
    -0.74
    uca
    -0.71
    abo
    -0.71
    ģĸ
    -0.69
    osterone
    -0.69
    imester
    -0.69
    otin
    -0.69
    olin
    -0.69
    iatrics
    -0.68
    POSITIVE LOGITS
     huh
    1.10
     eh
    0.99
     preferably
    0.97
    Excellent
    0.96
     lousy
    0.92
     flawless
    0.88
     lots
    0.87
     unbeat
    0.86
     excellent
    0.86
     decent
    0.86
    Activations Density 0.586%

    No Known Activations