© 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. 8-RES-JB
    11. 17832
    Prev
    Next
    INDEX
    Explanations

    prepositions preceding specific contexts or actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" and its contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATHER
    -0.63
     combatants
    -0.63
     awa
    -0.58
    weights
    -0.58
    ALSE
    -0.57
    ¶æ
    -0.57
    hur
    -0.56
    76561
    -0.56
    llan
    -0.55
    tre
    -0.54
    POSITIVE LOGITS
     spite
    1.40
     lieu
    1.32
     retrospect
    1.22
     addition
    1.18
     accordance
    1.16
     essence
    1.13
     conjunction
    1.08
     fact
    1.08
     hindsight
    1.08
    escap
    1.07
    Activations Density 0.159%

    No Known Activations