© 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. 9-RES-JB
    11. 10119
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative judgments or situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "poor."

    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
    ategory
    -0.99
    thus
    -0.71
    CU
    -0.70
    SPONSORED
    -0.68
    theless
    -0.67
    BuyableInstoreAndOnline
    -0.67
    Pi
    -0.67
    auer
    -0.66
    Laughs
    -0.66
    natureconservancy
    -0.65
    POSITIVE LOGITS
    die
    0.92
    dies
    0.89
     quality
    0.88
     souls
    0.88
    quality
    0.84
     luck
    0.84
     sap
    0.81
     grades
    0.81
     performers
    0.79
     imitation
    0.78
    Activations Density 0.036%

    No Known Activations