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. 6-RES-JB
    6. 53
    Prev
    Next
    INDEX
    Explanations

    phrases related to extremism, activism, and activism responses

    oai_token-act-pair · gpt-3.5-turbo

    the symbol 'âĢ' used in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.74
     grips
    -0.68
     Marble
    -0.68
     mant
    -0.68
     Reprodu
    -0.66
     division
    -0.66
     Elm
    -0.65
     Belg
    -0.63
     GPS
    -0.62
     raft
    -0.61
    POSITIVE LOGITS
    ª
    1.11
    ł
    1.04
    Ĵ
    1.04
    IJ
    1.03
    ¹
    1.03
    ij
    1.02
    against
    0.96
    ķ
    0.95
    Ķ
    0.94
    ¼
    0.94
    Activations Density 0.163%

    No Known Activations