© 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. 11-RES-JB
    11. 21263
    Prev
    Next
    INDEX
    Explanations

    phrases related to conspiracies or attempts to manipulate public opinion

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to conspiracy theories and political manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lication
    -1.00
    accompan
    -0.82
    eport
    -0.81
    ready
    -0.78
    spection
    -0.74
    apache
    -0.74
    living
    -0.73
    IFE
    -0.72
     Bei
    -0.71
    eways
    -0.71
    POSITIVE LOGITS
     undermine
    1.44
     manipulate
    1.40
     discredit
    1.37
     deceive
    1.36
     intimidate
    1.33
     distort
    1.29
     bully
    1.29
     smear
    1.29
     mislead
    1.27
     sow
    1.24
    Activations Density 0.268%

    No Known Activations