© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 14824
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the subsequent action or sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "follows"

    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
    amon
    -0.58
     hem
    -0.54
    rol
    -0.54
     bigger
    -0.52
    ender
    -0.52
    agate
    -0.51
     everyday
    -0.49
     anyway
    -0.49
    ering
    -0.49
    arlane
    -0.49
    POSITIVE LOGITS
     follows
    3.80
    follow
    1.79
     follow
    1.77
     followed
    1.76
     accompanies
    1.49
     following
    1.32
     revolves
    1.31
     ensued
    1.18
     emerges
    1.18
     preceded
    1.17
    Activations Density 0.011%

    No Known Activations