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. 10376
    Prev
    Next
    INDEX
    Explanations

    mentions of physical medical conditions and treatments like bandages

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "age" and related terms

    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
    ALLY
    -0.72
     stewards
    -0.67
    sw
    -0.66
    yss
    -0.65
    rise
    -0.64
    rip
    -0.60
    SW
    -0.59
    expr
    -0.59
     reconstruction
    -0.59
    RA
    -0.57
    POSITIVE LOGITS
    paces
    1.55
    pace
    1.45
    hips
    1.43
    hops
    1.39
    hift
    1.36
    omething
    1.36
    ystem
    1.34
    ettings
    1.32
    mith
    1.32
    ilver
    1.29
    Activations Density 0.182%

    No Known Activations