© 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. 6-RES-JB
    11. 2636
    Prev
    Next
    INDEX
    Explanations

    specific times of the day

    oai_token-act-pair · gpt-3.5-turbo

    specific times with a consistent focus on the hour and minute format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lessly
    -0.78
     STATS
    -0.73
    sole
    -0.71
    raltar
    -0.68
     pse
    -0.66
    orned
    -0.66
    aped
    -0.66
     endors
    -0.63
    agna
    -0.62
    rival
    -0.62
    POSITIVE LOGITS
    GMT
    1.00
    pm
    0.99
    PM
    0.99
     pm
    0.98
    AM
    0.82
     hrs
    0.78
     PDT
    0.77
     UTC
    0.77
     PM
    0.75
     PST
    0.75
    Activations Density 0.039%

    No Known Activations