© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 817
    Prev
    Next
    INDEX
    Explanations

    phrases describing actions being taken or statements being made by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "In" at the beginning of sentences or clauses

    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
     spoil
    -0.70
     looms
    -0.69
     lett
    -0.66
    76561
    -0.66
     lov
    -0.65
     lodged
    -0.64
    channelAvailability
    -0.63
     pim
    -0.62
     desired
    -0.61
    reon
    -0.61
    POSITIVE LOGITS
     addition
    1.25
    juries
    1.24
    ventory
    1.23
    cluding
    1.21
    jured
    1.19
    flation
    1.18
     spite
    1.17
    herent
    1.16
    clusion
    1.15
    coming
    1.14
    Activations Density 0.163%

    No Known Activations