© 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. 3563
    Prev
    Next
    INDEX
    Explanations

    currencies

    oai_token-act-pair · gpt-3.5-turbo

    references to the currency rupee

    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
    enegger
    -0.87
    RAFT
    -0.78
    icipated
    -0.76
    DragonMagazine
    -0.72
    ellar
    -0.67
    orsi
    -0.67
     Bastard
    -0.66
    aldehyde
    -0.66
     Dragonbound
    -0.65
     Gerry
    -0.65
    POSITIVE LOGITS
    pees
    1.38
     ru
    1.27
    pee
    1.10
    pling
    0.87
    eno
    0.77
    umat
    0.75
     penn
    0.75
    vers
    0.75
    enos
    0.73
    atra
    0.73
    Activations Density 0.004%

    No Known Activations