© 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. 7-RES-JB
    11. 1434
    Prev
    Next
    INDEX
    Explanations

    sentences related to philosophical and abstract discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to subjective evaluations or criticisms of artistic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Veterans
    -0.60
     Flam
    -0.58
     Adren
    -0.56
     Nepal
    -0.56
     Wildlife
    -0.55
     Dri
    -0.55
     Globe
    -0.54
     Sang
    -0.53
     Lunar
    -0.53
     Deng
    -0.53
    POSITIVE LOGITS
    )).
    0.84
    ?).
    0.83
     existed
    0.75
     infall
    0.74
     totality
    0.73
     oneself
    0.72
     objectively
    0.72
    actual
    0.70
     unlaw
    0.70
    ?".
    0.69
    Activations Density 1.353%

    No Known Activations