© 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. 10-RES-JB
    11. 7300
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" followed by a high context term

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shake
    -0.75
     stakes
    -0.61
     morale
    -0.60
     informants
    -0.60
    ebin
    -0.60
     grate
    -0.59
     dinners
    -0.59
     launch
    -0.58
     invoke
    -0.58
     upbringing
    -0.58
    POSITIVE LOGITS
    strument
    1.94
    visible
    1.78
    jured
    1.65
    jury
    1.64
    clusive
    1.64
    vasive
    1.62
    cluded
    1.60
    jected
    1.57
    flation
    1.54
    valid
    1.53
    Activations Density 0.064%

    No Known Activations