© 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. 373
    Prev
    Next
    INDEX
    Explanations

    mentions of hearing-related actions and medical terms

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to perception and understanding

    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
     phased
    -0.59
     whistleblower
    -0.55
     Architects
    -0.55
     Comet
    -0.53
     Tsu
    -0.53
    eatures
    -0.53
    zik
    -0.53
     Rollins
    -0.52
     Uz
    -0.52
    quartered
    -0.51
    POSITIVE LOGITS
     etc
    1.40
     thereof
    0.96
     alike
    0.90
    !/
    0.86
     versa
    0.86
     respectively
    0.83
     blah
    0.83
    etc
    0.81
     thereto
    0.80
     therein
    0.79
    Activations Density 0.674%

    No Known Activations