© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 897
    Prev
    Next
    INDEX
    Explanations

    phrases related to calling for an end to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to demands or calls for cessation or end

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.68
    matter
    -0.67
    wake
    -0.67
    Maker
    -0.66
    augh
    -0.64
    Brit
    -0.64
    brow
    -0.64
    folk
    -0.63
    ãĥij
    -0.63
    hew
    -0.62
    POSITIVE LOGITS
     hostilities
    1.21
     curfew
    0.88
     restrictions
    0.81
     slavery
    0.80
     bloodshed
    0.78
     austerity
    0.77
     segregation
    0.77
     homelessness
    0.77
     repression
    0.77
     compulsory
    0.77
    Activations Density 0.216%

    No Known Activations