© 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. 7-RES-JB
    11. 15191
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "it is" and "it's"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate likelihood or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bang
    -0.54
     Kenyan
    -0.53
     Pigs
    -0.53
    )"
    -0.53
     Sharia
    -0.53
     Kenya
    -0.52
    cohol
    -0.52
     Kuala
    -0.52
     Lit
    -0.51
     Brune
    -0.51
    POSITIVE LOGITS
    etheless
    0.87
    pmwiki
    0.71
     nonetheless
    0.68
    NetMessage
    0.61
    ãĥĩãĤ£
    0.61
    agonists
    0.61
     nevertheless
    0.59
    Sensor
    0.58
    ãĤ¦ãĤ¹
    0.57
     decidedly
    0.57
    Activations Density 1.087%

    No Known Activations