© 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. 1-RES-JB
    11. 9508
    Prev
    Next
    INDEX
    Explanations

    terms related to technology features that are 'enabled'

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology functionalities being activated or enabled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apest
    -0.83
    odor
    -0.79
    bons
    -0.78
    ogy
    -0.78
    andum
    -0.77
    alg
    -0.75
    WAR
    -0.69
    REF
    -0.66
    é¾įåĸļ士
    -0.65
    sem
    -0.65
    POSITIVE LOGITS
     enabled
    1.18
     confir
    0.87
     Enabled
    0.87
     guiActiveUn
    0.84
     enables
    0.81
     parity
    0.79
     showc
    0.78
    enabled
    0.76
    ioned
    0.75
     ashore
    0.75
    Activations Density 0.013%

    No Known Activations