Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2751
    Prev
    Next
    INDEX
    Explanations

    years from the 1960s

    oai_token-act-pair · gpt-3.5-turbo

    specific years, particularly those in the 1960s and 1970s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.79
    EStreamFrame
    -0.78
    edo
    -0.69
    zzle
    -0.66
    ndra
    -0.66
    parency
    -0.65
    hed
    -0.62
    itivity
    -0.61
    prime
    -0.61
    Sensor
    -0.59
    POSITIVE LOGITS
    -'
    0.79
    å¹
    0.77
     ILCS
    0.70
     Minutes
    0.70
    stones
    0.69
    çļ
    0.68
     Chevrolet
    0.66
    abad
    0.66
     BCE
    0.64
     Bomber
    0.64
    Activations Density 0.053%

    No Known Activations