© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17167
    Prev
    Next
    INDEX
    Explanations

    phrases related to asserting or contesting claims

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "claim."

    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
     arrang
    -0.87
     srf
    -0.86
     newcom
    -0.76
     electing
    -0.75
     Watching
    -0.73
     simul
    -0.73
     actionGroup
    -0.72
     destro
    -0.72
    cffffcc
    -0.67
    odes
    -0.66
    POSITIVE LOGITS
     claims
    0.93
    ylum
    0.86
    Claim
    0.85
    ifications
    0.82
    orial
    0.79
     claim
    0.78
    oux
    0.77
    ages
    0.77
    ulent
    0.76
     Cheong
    0.75
    Activations Density 0.024%

    No Known Activations