© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13547
    Prev
    Next
    INDEX
    Explanations

    mentions of dairy products, particularly cream

    oai_token-act-pair · gpt-3.5-turbo

    references to cream and its various usages or forms

    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
    vernment
    -0.69
     IMAGES
    -0.67
    NF
    -0.66
     WATCHED
    -0.64
    cffffcc
    -0.64
    bably
    -0.62
    ITCH
    -0.62
     Gamergate
    -0.61
     Prospect
    -0.60
     Standing
    -0.60
    POSITIVE LOGITS
    iness
    1.10
    cup
    1.08
     cheese
    0.96
    ery
    0.95
    erton
    0.95
    fields
    0.92
    maid
    0.89
    toe
    0.81
    nut
    0.81
    cream
    0.80
    Activations Density 0.034%

    No Known Activations