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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 17571
    Prev
    Next
    INDEX
    Explanations

    instances of words related to manipulation or control

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to manipulation and distortion of truth or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccoli
    -0.81
    starter
    -0.71
    ¯¯¯¯
    -0.70
    âĹ¼
    -0.70
    zik
    -0.69
    hesda
    -0.65
    SourceFile
    -0.65
    oother
    -0.65
    esides
    -0.65
    alone
    -0.64
    POSITIVE LOGITS
     perceptions
    1.16
     facts
    1.04
     reality
    1.01
     minds
    1.00
     realities
    0.96
     headlines
    0.92
     emotions
    0.92
     events
    0.89
     timelines
    0.87
     opinions
    0.84
    Activations Density 0.193%

    No Known Activations