© 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. 9-RES-JB
    11. 5317
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong opinions, criticism, and potentially controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    themes related to conflict and opposition in societal discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.79
     reluct
    -0.71
    ãĥ¼ãĥ³
    -0.68
    ahead
    -0.66
     encount
    -0.65
     conclud
    -0.63
    never
    -0.63
     dummy
    -0.62
     absorbed
    -0.61
    riad
    -0.60
    POSITIVE LOGITS
     Islam
    1.01
     theirs
    0.98
     ours
    0.93
     us
    0.89
     them
    0.88
     injustice
    0.86
     humanity
    0.85
     oppression
    0.81
     him
    0.81
     yours
    0.80
    Activations Density 0.487%

    No Known Activations