© 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. 2-RES-JB
    11. 23477
    Prev
    Next
    INDEX
    Explanations

    words related to oppression or suppression

    oai_token-act-pair · gpt-3.5-turbo

    expressions of suppression or negative sentiments regarding freedom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Stars
    -0.64
     Ore
    -0.61
     Ceres
    -0.60
    whe
    -0.60
    igmatic
    -0.59
    leaf
    -0.59
     Hale
    -0.59
     CMS
    -0.58
    bright
    -0.57
    ready
    -0.56
    POSITIVE LOGITS
    ategory
    0.92
    terness
    0.88
    elist
    0.85
    wart
    0.84
    hovah
    0.83
    utsche
    0.79
    ofi
    0.75
    nesses
    0.74
     disadvant
    0.74
    SPONSORED
    0.71
    Activations Density 0.143%

    No Known Activations