© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11985
    Prev
    Next
    INDEX
    Explanations

    phrases related to instigating, initiating, or inciting actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "install" and its variations

    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
    theless
    -0.84
     Tone
    -0.82
    ãĥīãĥ©ãĤ´ãĥ³
    -0.68
    ALD
    -0.67
    DEN
    -0.67
    dylib
    -0.66
    Ô
    -0.66
    berries
    -0.64
    TEXTURE
    -0.63
    SHIP
    -0.62
    POSITIVE LOGITS
    itutional
    1.28
    inct
    1.24
    itution
    1.19
    itute
    1.15
    agram
    1.12
    igator
    1.08
    alling
    1.07
    illation
    1.06
    ruction
    1.06
    alled
    1.04
    Activations Density 0.014%

    No Known Activations