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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 20212
    Prev
    Next
    INDEX
    Explanations

    lines of text ending with a specific character as indicated by the colon with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    sequences of punctuation marks and structured text elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leaks
    -0.78
     ingred
    -0.70
    soDeliveryDate
    -0.68
     hemor
    -0.67
    æ©
    -0.66
     pestic
    -0.65
     principals
    -0.65
    ensibly
    -0.64
     exting
    -0.64
     Palestin
    -0.61
    POSITIVE LOGITS
     âĨij
    0.89
    Show
    0.76
     Adding
    0.69
     Originally
    0.68
     Cly
    0.68
     Interesting
    0.66
    itars
    0.65
    leon
    0.64
    Originally
    0.64
     inherit
    0.63
    Activations Density 0.071%

    No Known Activations