© 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. 2-RES-JB
    11. 17842
    Prev
    Next
    INDEX
    Explanations

    mentions of specific food items, particularly cereals

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of cereals and grains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.69
    affer
    -0.65
    lihood
    -0.64
    hare
    -0.64
    jury
    -0.64
    istance
    -0.64
    ount
    -0.63
     prosec
    -0.63
    CVE
    -0.63
    swer
    -0.62
    POSITIVE LOGITS
     cereal
    1.18
     cere
    1.08
    grain
    0.95
     grains
    0.88
     biscuits
    0.84
     flav
    0.83
     Cere
    0.81
    beans
    0.81
    weed
    0.80
    stal
    0.79
    Activations Density 0.014%

    No Known Activations