© 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. 6-RES-JB
    11. 10740
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a direction, such as "to" or "in", often indicating a relationship between entities

    oai_token-act-pair · gpt-3.5-turbo

    dominant prepositions and additional context words in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoe
    -0.67
    orks
    -0.64
    º
    -0.61
    fter
    -0.61
     Lines
    -0.60
    âĸij
    -0.59
    ealous
    -0.59
     forgot
    -0.59
    vier
    -0.59
    ato
    -0.59
    POSITIVE LOGITS
    arching
    0.71
     WW
    0.70
     regard
    0.66
     redeem
    0.63
    isSpecialOrderable
    0.60
     Concord
    0.60
     augment
    0.60
     govern
    0.59
     appeal
    0.58
     Qt
    0.58
    Activations Density 0.221%

    No Known Activations