© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22172
    Prev
    Next
    INDEX
    Explanations

    actions followed by a subsequent action

    oai_token-act-pair · gpt-3.5-turbo

    the transition word "then" to indicate subsequent actions or events

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

    No Comments

    Negative Logits
    undo
    -0.72
    FORE
    -0.66
    Latin
    -0.65
    sth
    -0.64
    idad
    -0.64
    toe
    -0.63
    MpServer
    -0.61
    borgh
    -0.59
    faced
    -0.59
    orde
    -0.59
    POSITIVE LOGITS
     proceeded
    1.07
     secondly
    0.84
     proceed
    0.81
     conclud
    0.81
     succumb
    0.79
    )</
    0.79
     promptly
    0.77
     tyr
    0.76
     afterward
    0.75
    forth
    0.75
    Activations Density 0.036%

    No Known Activations