© 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. 2-RES-JB
    11. 13453
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to 'ank'

    oai_token-act-pair · gpt-3.5-turbo

    words or terms associated with "bank."

    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
     sclerosis
    -0.64
     isot
    -0.63
     redistributed
    -0.62
     cryst
    -0.61
     compr
    -0.61
    ccording
    -0.59
    perature
    -0.59
     discrim
    -0.58
     fluids
    -0.57
     skelet
    -0.57
    POSITIVE LOGITS
    ank
    1.09
    ernel
    0.90
    furt
    0.88
    arthed
    0.86
    uild
    0.86
    ular
    0.84
    aly
    0.83
    aran
    0.82
    ula
    0.82
    iewicz
    0.82
    Activations Density 0.007%

    No Known Activations