Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 3517
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of emerald

    oai_token-act-pair · gpt-3.5-turbo

    terms related to emergency situations or phenomena

    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
     guiActiveUnfocused
    -0.80
     Liberals
    -0.73
     Suc
    -0.71
     Passenger
    -0.71
    EngineDebug
    -0.68
     Ukrainians
    -0.67
    Buzz
    -0.66
     Carney
    -0.65
     Comfort
    -0.64
     Tens
    -0.63
    POSITIVE LOGITS
    ira
    1.00
     emer
    0.98
    ald
    0.95
    oing
    0.89
    ucl
    0.84
    idian
    0.83
    andum
    0.79
    oint
    0.78
    plementation
    0.75
    roach
    0.74
    Activations Density 0.011%

    No Known Activations