© 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. 20429
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Day" with different lengths of day

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific months mentioned in dates

    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
    atem
    -0.72
    Interstitial
    -0.70
     princ
    -0.69
    ļéĨĴ
    -0.65
     looph
    -0.64
     arrang
    -0.64
    keyes
    -0.63
     proble
    -0.62
    arantine
    -0.62
    essors
    -0.61
    POSITIVE LOGITS
     2017
    0.89
     2018
    0.87
     27
    0.85
     28
    0.83
     29
    0.81
     04
    0.81
     06
    0.80
     05
    0.80
     07
    0.79
    hew
    0.78
    Activations Density 0.084%

    No Known Activations