© 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. 19804
    Prev
    Next
    INDEX
    Explanations

    specific dates in the format "ago X", where X is a number representing the time in the past

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating time or temporal references

    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
     mathemat
    -0.95
     suspic
    -0.84
     belie
    -0.78
     plaus
    -0.75
     challeng
    -0.72
     glim
    -0.68
     sclerosis
    -0.67
    ifying
    -0.66
     uniqueness
    -0.65
    lining
    -0.65
    POSITIVE LOGITS
    vernment
    1.38
    zzi
    1.01
    onga
    0.99
    edia
    0.94
    asca
    0.92
    zzo
    0.88
    xon
    0.87
    zeb
    0.83
    orthy
    0.82
    unin
    0.82
    Activations Density 0.020%

    No Known Activations