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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 23615
    Prev
    Next
    INDEX
    Explanations

    phrases related to analysis, consistency, cohesion, enthusiasm, dedication, texture, expression, innovation, discipline, inspiration, energy, vision, integrity, support, and accountability

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with concepts of integrity, support, and community values

    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
    pload
    -0.78
    iannopoulos
    -0.77
    abet
    -0.76
    iann
    -0.74
    aceae
    -0.73
    kernel
    -0.70
    otin
    -0.70
    ipel
    -0.67
    iov
    -0.66
    weeney
    -0.65
    POSITIVE LOGITS
     alike
    1.46
     thereof
    1.11
     respectively
    0.87
     versa
    0.80
     accordingly
    0.77
     thereto
    0.77
     therein
    0.72
     consequ
    0.70
     amongst
    0.67
     barriers
    0.66
    Activations Density 0.402%

    No Known Activations