© 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. 4220
    Prev
    Next
    INDEX
    Explanations

    the word 'a'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" 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 @ 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
    Edit
    -0.77
    otte
    -0.77
    effects
    -0.73
    hours
    -0.73
    Events
    -0.72
    Versions
    -0.71
    acid
    -0.69
    alks
    -0.69
    End
    -0.69
    AIDS
    -0.67
    POSITIVE LOGITS
     lot
    1.27
     reminder
    1.20
     bit
    1.19
     tad
    1.15
     HUGE
    1.13
     testament
    1.13
     huge
    1.13
     pretty
    1.05
     nice
    1.01
     definite
    1.01
    Activations Density 0.223%

    No Known Activations