© 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. 8-RES-JB
    11. 18642
    Prev
    Next
    INDEX
    Explanations

    actions involving movement and interaction between characters in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitions that indicate sequential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.79
    etheless
    -0.76
    relevant
    -0.75
    Gamer
    -0.74
    uthor
    -0.73
    ensor
    -0.72
    appropriate
    -0.72
    responsible
    -0.71
    MK
    -0.70
    icularly
    -0.70
    POSITIVE LOGITS
     began
    1.11
     proceeded
    1.05
     then
    1.05
     stared
    0.94
     shook
    0.93
     promptly
    0.93
     waited
    0.92
     threw
    0.91
     took
    0.91
     glanced
    0.91
    Activations Density 0.200%

    No Known Activations