© 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. 4967
    Prev
    Next
    INDEX
    Explanations

    words related to specific targeting or focus on a particular group or entity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of targeting in various contexts

    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
    lycer
    -0.79
    fo
    -0.78
    loo
    -0.78
    rar
    -0.76
    batch
    -0.75
    heit
    -0.74
    iHUD
    -0.73
    ston
    -0.66
    wine
    -0.66
    riger
    -0.65
    POSITIVE LOGITS
    ted
    0.92
     squarely
    0.78
     specificity
    0.77
     targets
    0.77
     killings
    0.76
     targeted
    0.74
     assass
    0.74
     targeting
    0.74
    eers
    0.72
     specific
    0.72
    Activations Density 0.052%

    No Known Activations