© 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. 3-RES-JB
    11. 13379
    Prev
    Next
    INDEX
    Explanations

    dates or days of the week

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days, events, and occurrences related to Sunday and Tuesday

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -1.02
    ongh
    -0.88
    adem
    -0.71
    insured
    -0.70
    vae
    -0.70
    idated
    -0.69
     collaborations
    -0.66
    exempt
    -0.65
     counterfe
    -0.65
    avorite
    -0.65
    POSITIVE LOGITS
    morning
    0.86
     eve
    0.80
    night
    0.75
     anniversary
    0.73
    Lewis
    0.71
    iversary
    0.70
     cycle
    0.69
     Eid
    0.69
     recess
    0.68
     Topic
    0.68
    Activations Density 0.557%

    No Known Activations