© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17997
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and news topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" and related phrases indicating context or discussion points

    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
    INFO
    -0.74
    crypt
    -0.70
    fort
    -0.70
    ~~~~~~~~
    -0.67
    printf
    -0.67
    iren
    -0.67
    tumblr
    -0.66
    Copy
    -0.66
    Champ
    -0.65
    ãĤ¨
    -0.64
    POSITIVE LOGITS
     wanting
    0.80
    igating
    0.77
     himself
    0.76
     introducing
    0.75
     herself
    0.75
     commencement
    0.71
     retiring
    0.70
     quitting
    0.70
     regrets
    0.70
     Rhod
    0.67
    Activations Density 0.308%

    No Known Activations