© 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. 10143
    Prev
    Next
    INDEX
    Explanations

    Brazilian Portuguese diacritics used in words

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "didn't" in various contexts

    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
     hemor
    -0.75
     mathemat
    -0.74
     subsequ
    -0.72
     Seym
    -0.70
     imitation
    -0.69
     captives
    -0.69
     successes
    -0.66
     Swordsman
    -0.65
     culprit
    -0.65
     defeats
    -0.65
    POSITIVE LOGITS
    ï¸ı
    1.03
    Balt
    0.96
    sure
    0.94
    ï¸
    0.93
    âĢł
    0.87
    ski
    0.85
    own
    0.85
    âķIJ
    0.84
    atural
    0.82
    _>
    0.82
    Activations Density 0.254%

    No Known Activations