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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 18396
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Del" followed by a digit

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific entity or brand named "Del."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moonlight
    -0.73
    SHIP
    -0.70
    OLOGY
    -0.66
     AFL
    -0.66
    beans
    -0.65
    ĸļ
    -0.64
     FTA
    -0.62
     Emmanuel
    -0.62
    doms
    -0.60
     ASA
    -0.60
    POSITIVE LOGITS
    ayed
    1.27
    icate
    1.24
    usional
    1.21
    ivery
    1.19
    aware
    1.16
    ivered
    1.15
    phi
    1.15
    ivering
    1.14
    inqu
    1.11
    iber
    1.08
    Activations Density 0.016%

    No Known Activations