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. 5-RES-JB
    6. 4664
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning or creating something specific with intention

    oai_token-act-pair · gpt-3.5-turbo

    statements that begin with the article "a" indicating formulation of ideas or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anism
    -0.78
    agents
    -0.76
    words
    -0.70
    Tip
    -0.69
    !/
    -0.67
    seekers
    -0.66
    iev
    -0.66
    mong
    -0.65
    aunts
    -0.65
    effects
    -0.64
    POSITIVE LOGITS
     bunch
    1.07
     new
    1.02
     plethora
    1.02
     lot
    1.00
     sizable
    0.96
     definitive
    0.93
     sizeable
    0.93
     permanent
    0.92
     meaningful
    0.90
     huge
    0.89
    Activations Density 0.461%

    No Known Activations