© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18842
    Prev
    Next
    INDEX
    Explanations

    the word "Camp" followed by a digit

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Camp" in various contexts

    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
    scill
    -0.80
    rx
    -0.78
     payable
    -0.74
     Rx
    -0.70
    nir
    -0.70
    trl
    -0.69
     enumer
    -0.69
     algorith
    -0.68
     handshake
    -0.67
     entropy
    -0.66
    POSITIVE LOGITS
     Camp
    3.97
    Camp
    2.84
    camp
    2.45
     camp
    2.37
     camps
    2.08
     camping
    1.55
     Ranch
    1.27
     Campbell
    1.27
     tents
    1.25
     encamp
    1.23
    Activations Density 0.010%

    No Known Activations