© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10679
    Prev
    Next
    INDEX
    Explanations

    Invitations or references to events happening during the evening or nighttime

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "tonight."

    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
    llor
    -0.82
    sac
    -0.77
    egal
    -0.70
    Pros
    -0.68
    vet
    -0.68
    76561
    -0.67
    insured
    -0.66
    ophers
    -0.66
    hetti
    -0.66
    regon
    -0.65
    POSITIVE LOGITS
     tonight
    1.05
     afternoon
    1.05
     morning
    0.99
     evening
    0.98
    Tonight
    0.97
     Tonight
    0.93
     night
    0.90
     Evening
    0.84
    night
    0.82
     Hots
    0.79
    Activations Density 0.005%

    No Known Activations