© 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. 17876
    Prev
    Next
    INDEX
    Explanations

    mentions of a small quantity or limited number of items

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "handful" used to describe a small quantity

    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
    mediate
    -0.80
    abolic
    -0.72
    ATHER
    -0.67
    agnar
    -0.66
    Train
    -0.65
    thur
    -0.65
    ogens
    -0.65
    atro
    -0.64
    hemat
    -0.63
    Definition
    -0.63
    POSITIVE LOGITS
     dozen
    0.94
    eenth
    0.87
     handful
    0.86
    een
    0.84
    dozen
    0.76
    ãĤ©
    0.75
    ĸļ
    0.74
    otaur
    0.74
     thousand
    0.73
     hundred
    0.72
    Activations Density 0.006%

    No Known Activations