© 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. 8-RES-JB
    11. 18464
    Prev
    Next
    INDEX
    Explanations

    numerical structures such as lists or countdowns

    oai_token-act-pair · gpt-3.5-turbo

    the repeated appearance of a specific character or symbol

    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
     adolesc
    -0.66
     suicide
    -0.65
     ignition
    -0.64
     Morse
    -0.63
     Spot
    -0.63
     Stuff
    -0.62
     Lancaster
    -0.62
    undown
    -0.61
     Antar
    -0.61
     Addiction
    -0.60
    POSITIVE LOGITS
    agree
    1.02
    own
    0.98
    ï¸ı
    0.97
    should
    0.89
    felt
    0.87
    mand
    0.87
    tarians
    0.84
    tu
    0.84
     selves
    0.83
    ould
    0.83
    Activations Density 0.161%

    No Known Activations