© 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. 23816
    Prev
    Next
    INDEX
    Explanations

    Capitalized words with 'off' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the concept of being turned off or deactivated

    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
    ãĤ§
    -0.79
    SHARE
    -0.67
    д
    -0.65
     corrid
    -0.65
    ãĥ£
    -0.63
    ãĤ©
    -0.63
    CVE
    -0.62
    ãĥ¥
    -0.62
     tremend
    -0.62
    entary
    -0.61
    POSITIVE LOGITS
    ices
    1.01
    ense
    0.96
    rey
    0.93
    erence
    0.92
    ishly
    0.88
    ersen
    0.87
    oons
    0.86
    enders
    0.82
    erson
    0.79
    spring
    0.78
    Activations Density 0.022%

    No Known Activations