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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 6728
    Prev
    Next
    INDEX
    Explanations

    imperative verb phrases related to requests or demands

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or requests for government or organizational intervention

    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
     Kop
    -0.66
    traumatic
    -0.66
    furt
    -0.63
    Flo
    -0.63
    ãĤ¼
    -0.62
    Got
    -0.60
     Malk
    -0.59
    radio
    -0.58
    Talking
    -0.57
     adolesc
    -0.57
    POSITIVE LOGITS
     reconsider
    1.30
     investigate
    1.14
     clarify
    1.10
     intervene
    1.07
     disclose
    1.05
     revise
    1.05
     undertake
    1.04
     appoint
    1.02
     abolish
    0.97
     abandon
    0.97
    Activations Density 0.182%

    No Known Activations