© 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. 4-RES-JB
    11. 4095
    Prev
    Next
    INDEX
    Explanations

    terms related to specific brands or names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific brands or names related to vehicles and appliances

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

    No Comments

    Negative Logits
    iddles
    -1.03
    abis
    -0.83
    edly
    -0.82
    ngth
    -0.80
    itsch
    -0.74
    blance
    -0.74
    gdala
    -0.70
    hot
    -0.70
    llah
    -0.70
    myra
    -0.70
    POSITIVE LOGITS
    ãĥīãĥ©
    0.90
     Volvo
    0.89
     Siem
    0.67
     Frankenstein
    0.65
    urus
    0.65
    ãĢIJ
    0.64
     Sheen
    0.63
     Sven
    0.63
     Ocean
    0.62
     Drac
    0.62
    Activations Density 0.028%

    No Known Activations