© 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. 4-RES-JB
    11. 10222
    Prev
    Next
    INDEX
    Explanations

    specific times of the day, particularly in the early morning

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific times in the morning, particularly times associated with 'am'

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

    No Comments

    Negative Logits
     resemb
    -0.71
     behav
    -0.69
    ollah
    -0.69
     unequ
    -0.67
     recre
    -0.59
     kinderg
    -0.59
    kefeller
    -0.58
     Cos
    -0.57
     tremend
    -0.57
     prescription
    -0.56
    POSITIVE LOGITS
    endment
    1.29
     EDT
    0.98
    nesty
    0.96
     EST
    0.93
    obile
    0.88
     PST
    0.87
    sterdam
    0.86
     PDT
    0.86
    ateur
    0.84
     onwards
    0.83
    Activations Density 0.016%

    No Known Activations