© 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. 4-RES-JB
    11. 17323
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Banana"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "banana" and related terms

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

    No Comments

    Negative Logits
    atically
    -0.81
    apping
    -0.79
    ipeg
    -0.79
    apped
    -0.75
    uper
    -0.73
    itance
    -0.72
    ourney
    -0.72
    actly
    -0.72
    apes
    -0.70
    ACY
    -0.70
    POSITIVE LOGITS
    hari
    0.80
    luaj
    0.80
    MpServer
    0.70
    hee
    0.69
    SourceFile
    0.69
    jamin
    0.68
    emonium
    0.66
    ocular
    0.65
    ħĭ
    0.65
    etheless
    0.64
    Activations Density 0.026%

    No Known Activations