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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 0-RES-JB
    6. 8201
    Prev
    Next
    INDEX
    Explanations

    words with special characters, possibly indicating encoding errors or language variations

    oai_token-act-pair · gpt-3.5-turbo

    patterns of emphasis or stress on certain terms or phrases reflecting digital media influence, particularly in relation to youth engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "...
    -0.93
     -
    -0.85
     -----
    -0.76
    nesday
    -0.71
     (-
    -0.70
    ...?
    -0.68
    anwhile
    -0.67
     Pastebin
    -0.66
    ĸļ
    -0.66
    ramid
    -0.66
    POSITIVE LOGITS
    ÂŃ
    3.91
     ÂŃ
    2.71
    âĢIJ
    2.12
    âĢij
    2.01
     
    1.58
    îĢ
    1.40
      
    1.38
    ÃĤ
    1.32
    –
    1.29
      
    1.28
    Activations Density 0.008%

    No Known Activations