© 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. 509
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and computer culture

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word 'nerd' and related terms, as well as references to declassification

    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
     Cipher
    -0.68
    åĮ
    -0.68
     FISA
    -0.66
    Multiple
    -0.63
     CPC
    -0.62
    EVA
    -0.61
    å½
    -0.61
     Beautiful
    -0.61
    achusetts
    -0.60
    Mary
    -0.60
    POSITIVE LOGITS
    linger
    0.98
    icer
    0.95
    pei
    0.92
    urt
    0.91
    geon
    0.86
    oji
    0.85
     Ner
    0.83
    dy
    0.81
    ding
    0.80
    elling
    0.80
    Activations Density 0.004%

    No Known Activations