© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10059
    Prev
    Next
    INDEX
    Explanations

    text fragments containing communication patterns like email responses

    oai_token-act-pair · gpt-3.5-turbo

    instances of written correspondence or email formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adversaries
    -0.68
     principals
    -0.68
    æ©
    -0.67
     comprom
    -0.66
     marches
    -0.64
     lenders
    -0.62
     exting
    -0.62
    åĤ
    -0.62
    angering
    -0.62
     escal
    -0.61
    POSITIVE LOGITS
     Quote
    1.18
    Hi
    1.17
    Excellent
    1.16
    Quote
    1.16
    Nice
    1.13
    Hello
    1.11
    Originally
    1.11
    wow
    1.10
    nice
    1.10
    yeah
    1.08
    Activations Density 0.106%

    No Known Activations