© 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. 9-RES-JB
    11. 16429
    Prev
    Next
    INDEX
    Explanations

    prepositions signaling actions or directions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the act of naming or listing examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦
    -0.54
     TAMADRA
    -0.54
     (&
    -0.54
    aren
    -0.53
    wire
    -0.51
     stripped
    -0.51
    need
    -0.51
    rows
    -0.51
     BEFORE
    -0.51
    enance
    -0.50
    POSITIVE LOGITS
    ggles
    1.13
    wered
    1.09
    adies
    0.99
    asted
    0.98
    ilet
    0.94
    othy
    0.91
    days
    0.90
    psy
    0.88
    pless
    0.87
    ffee
    0.85
    Activations Density 0.160%

    No Known Activations