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. 1-RES-JB
    6. 1871
    Prev
    Next
    INDEX
    Explanations

    words related to improvement, enhancement, or transformation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rev" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fine
    -0.72
    女
    -0.70
     Tale
    -0.69
     Horde
    -0.68
    Streamer
    -0.68
     Kant
    -0.67
     Fields
    -0.67
    ãģ¦
    -0.66
    Craft
    -0.66
    Frameworks
    -0.66
    POSITIVE LOGITS
     rev
    1.06
    ulsion
    1.02
    ivals
    1.02
    ascular
    0.93
    olve
    0.93
    oking
    0.92
    amping
    0.89
    ocations
    0.88
    iless
    0.88
    ision
    0.85
    Activations Density 0.008%

    No Known Activations