© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 7618
    Prev
    Next
    INDEX
    Explanations

    terms related to file formats, specifically looking for references to 'del' which could indicate the delimiter used, such as 'tab-delimited', 'comma-delimited', etc

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "del" in various forms

    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
     Asians
    -0.80
     Magnus
    -0.79
    atives
    -0.75
     POV
    -0.73
     Asian
    -0.67
     Ivy
    -0.66
     Prism
    -0.64
     circle
    -0.63
     OpenGL
    -0.62
     stat
    -0.62
    POSITIVE LOGITS
    del
    4.15
    Del
    2.11
     DEL
    1.79
     Del
    1.56
     del
    1.36
    de
    1.24
    Delivery
    1.23
    dal
    1.23
    des
    1.23
     Deliver
    1.18
    Activations Density 0.010%

    No Known Activations