© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 22688
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "like."

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or phrases indicating similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.74
    lication
    -0.73
    CHAT
    -0.72
    xit
    -0.72
     Phi
    -0.69
     Bravo
    -0.67
     throats
    -0.66
     VIDEOS
    -0.59
     Glory
    -0.58
     recip
    -0.58
    POSITIVE LOGITS
    olar
    0.68
    rylic
    0.67
    èª
    0.65
     overlooked
    0.64
    atten
    0.63
    aunt
    0.63
    rid
    0.62
    iod
    0.62
    pace
    0.62
     imaginable
    0.61
    Activations Density 0.144%

    No Known Activations