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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 10205
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" and its contextual significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irl
    -0.69
    abal
    -0.69
    dad
    -0.69
    ratulations
    -0.68
    edly
    -0.68
    ãĤ©
    -0.68
     Nope
    -0.68
    dies
    -0.66
    çĶ°
    -0.66
    KNOWN
    -0.66
    POSITIVE LOGITS
     order
    1.52
     accordance
    1.41
     lieu
    1.29
     case
    1.24
     conjunction
    1.17
     advance
    1.11
     anticipation
    1.10
     regards
    1.09
     relation
    1.06
     addition
    1.05
    Activations Density 0.254%

    No Known Activations