© 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. 1-RES-JB
    11. 22396
    Prev
    Next
    INDEX
    Explanations

    words related to a particular name "Aman"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Aman"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beir
    -0.65
     Peg
    -0.65
     Hegel
    -0.65
    Performance
    -0.63
    VALUE
    -0.63
     Scand
    -0.63
     Grind
    -0.62
    PRES
    -0.61
    FB
    -0.60
    REE
    -0.59
    POSITIVE LOGITS
    aman
    1.53
    ufact
    1.07
    iac
    1.03
    ovan
    1.03
    omon
    1.01
    icate
    1.00
    geon
    0.99
    tha
    0.97
    ovic
    0.97
    ican
    0.95
    Activations Density 0.007%

    No Known Activations