Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10297
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dog."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dogs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oulos
    -0.82
    éĹĺ
    -0.80
    ORN
    -0.73
    farious
    -0.72
     Sins
    -0.68
     WARN
    -0.67
    aic
    -0.67
     Hass
    -0.67
    DERR
    -0.66
     Occupations
    -0.65
    POSITIVE LOGITS
    Dog
    1.06
     dog
    1.04
     dogs
    1.00
    patch
    0.98
    meat
    0.94
     barking
    0.92
    fighter
    0.91
     pup
    0.90
    dog
    0.89
    matically
    0.88
    Activations Density 0.023%

    No Known Activations