© 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
    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. 490
    Prev
    Next
    INDEX
    Explanations

    keywords related to the city of Krakow

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ow"

    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
     Gemini
    -0.66
     serotonin
    -0.63
     Carbuncle
    -0.59
     vag
    -0.58
     ISS
    -0.57
     escal
    -0.57
     nerves
    -0.56
     nerve
    -0.56
     Pegasus
    -0.56
     Extras
    -0.55
    POSITIVE LOGITS
    ow
    4.34
    ows
    2.45
    owe
    2.41
    owed
    2.07
    owing
    2.03
    OW
    1.98
    owan
    1.58
    ower
    1.54
    oway
    1.52
    owell
    1.49
    Activations Density 0.009%

    No Known Activations