© 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. 8-RES-JB
    11. 7093
    Prev
    Next
    INDEX
    Explanations

    sentences related to political and social issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express resistance or refusal to cooperate with authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sequently
    -0.69
    oche
    -0.67
    inguished
    -0.65
    nown
    -0.63
     respectively
    -0.63
    including
    -0.62
    aran
    -0.59
    staking
    -0.59
    çĶ°
    -0.59
    yssey
    -0.58
    POSITIVE LOGITS
     crappy
    0.97
     shitty
    0.92
     crap
    0.91
     stuff
    0.84
     somebody
    0.78
     shit
    0.74
     dudes
    0.74
     oneself
    0.73
     passively
    0.72
     mediocre
    0.72
    Activations Density 1.451%

    No Known Activations