Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14400
    Prev
    Next
    INDEX
    Explanations

    phrases related to closing, stopping, or shutting down something

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with being silenced or shut down

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.69
    IVES
    -0.66
    ordan
    -0.63
    arya
    -0.62
     abund
    -0.62
    ampton
    -0.59
     Amit
    -0.58
    ãĥīãĥ©ãĤ´ãĥ³
    -0.58
     covari
    -0.57
    ALLY
    -0.57
    POSITIVE LOGITS
    tered
    1.60
    tering
    1.43
    downs
    1.14
    down
    1.13
    ters
    1.07
     down
    1.05
    tle
    1.05
    offs
    0.92
    own
    0.91
     downs
    0.88
    Activations Density 0.026%

    No Known Activations