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. 9-RES-JB
    6. 12435
    Prev
    Next
    INDEX
    Explanations

    mentions of dogs or dog-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to dogs

    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
    •dogs

    No Comments

    Negative Logits
    éĹĺ
    -0.84
    DERR
    -0.84
     Edison
    -0.78
    esson
    -0.75
    artz
    -0.75
    velength
    -0.70
    erences
    -0.70
    ISTER
    -0.67
    itures
    -0.66
    iary
    -0.66
    POSITIVE LOGITS
    gie
    1.19
    patch
    1.08
     barking
    1.08
    fight
    1.08
    shit
    1.03
    fighting
    1.03
    matically
    1.02
    matic
    1.00
    fights
    1.00
    meat
    0.98
    Activations Density 0.047%

    No Known Activations