© 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. 11-RES-JB
    11. 9889
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and system setup

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and codes related to software or programming options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atoon
    -0.76
    anta
    -0.71
    ande
    -0.70
    antz
    -0.69
    accompanied
    -0.68
    orno
    -0.66
    ageddon
    -0.65
    hens
    -0.65
    aye
    -0.65
    iste
    -0.64
    POSITIVE LOGITS
    FILE
    1.79
    PATH
    1.73
    NAME
    1.73
    SIZE
    1.72
    TIME
    1.68
    DIR
    1.68
    TYPE
    1.67
    USER
    1.66
    MODE
    1.64
    WARE
    1.62
    Activations Density 0.098%

    No Known Activations