© 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. 10238
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the word "for" in various contexts

    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
     srfAttach
    -0.65
    è¦ļéĨĴ
    -0.62
     dod
    -0.62
    VERTISEMENT
    -0.60
     oust
    -0.59
     litter
    -0.58
    itent
    -0.58
     nun
    -0.58
     eh
    -0.58
     belly
    -0.56
    POSITIVE LOGITS
    gotten
    1.39
    bidden
    1.37
    theless
    1.13
    gettable
    1.08
    giving
    0.99
    wards
    0.97
    rontal
    0.97
    give
    0.96
    getting
    0.96
    etheless
    0.94
    Activations Density 0.015%

    No Known Activations