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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 3169
    Prev
    Next
    INDEX
    Explanations

    phrases related to different phases or stages of a project or plan

    oai_token-act-pair · gpt-3.5-turbo

    references to phases in a series or project

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obsc
    -0.77
     consolation
    -0.74
     confession
    -0.74
     advoc
    -0.73
     apology
    -0.72
     interpreter
    -0.71
     broadcaster
    -0.71
     offend
    -0.71
     distur
    -0.71
     confessions
    -0.69
    POSITIVE LOGITS
     Phase
    3.37
    Phase
    2.55
     Stage
    1.77
     Step
    1.53
    phase
    1.44
    Stage
    1.37
     Wave
    1.15
     Route
    1.04
     Timeline
    1.03
     Steps
    1.02
    Activations Density 0.044%

    No Known Activations