© 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. 6-RES-JB
    6. 762
    Prev
    Next
    INDEX
    Explanations

    references to frozen water in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to ice in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entary
    -0.83
    nesday
    -0.81
    rompt
    -0.81
    ivating
    -0.80
    ilitary
    -0.76
    enance
    -0.76
     candidates
    -0.74
    ENTION
    -0.74
    sembly
    -0.73
    merce
    -0.73
    POSITIVE LOGITS
     cream
    1.17
    breaker
    1.13
     rink
    1.10
    breakers
    1.10
    cream
    1.07
     skating
    0.98
     crystals
    0.90
    flake
    0.87
    pick
    0.86
     Cream
    0.84
    Activations Density 0.023%

    No Known Activations