© 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. 7-RES-JB
    11. 133
    Prev
    Next
    INDEX
    Explanations

    words related to commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating refusal or rejection

    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
    ggles
    -0.70
     ingenious
    -0.70
     knack
    -0.68
    amiliar
    -0.68
    albeit
    -0.66
    staking
    -0.65
     adept
    -0.65
     nifty
    -0.64
    eely
    -0.63
    maxwell
    -0.61
    POSITIVE LOGITS
     anymore
    1.81
     nor
    1.27
     any
    1.08
     whatsoever
    1.08
     ANY
    1.07
     unless
    1.02
     anything
    1.02
     anywhere
    0.99
     anytime
    0.98
     EVER
    0.98
    Activations Density 0.639%

    No Known Activations