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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18036
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter combination "Th" in the text

    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
     shorth
    -0.70
     Cerberus
    -0.63
    âĸ¬âĸ¬
    -0.63
    keeping
    -0.61
     lapse
    -0.61
     PTSD
    -0.61
     labelled
    -0.61
     cabinets
    -0.60
     clearance
    -0.59
     sto
    -0.59
    POSITIVE LOGITS
    irteen
    1.40
    reshold
    1.28
    ought
    1.26
    ailand
    1.23
    orns
    1.22
    ousand
    1.18
    ttp
    1.18
    ieves
    1.15
    orne
    1.15
    rowing
    1.12
    Activations Density 0.025%

    No Known Activations