© 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. 9-RES-JB
    11. 1051
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical or negative assessments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating long-term relationships or commitments

    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
     charms
    -0.86
     Clubs
    -0.80
     domains
    -0.80
     magazines
    -0.76
     radios
    -0.76
     establishments
    -0.75
     clubs
    -0.74
     idols
    -0.74
     launchers
    -0.73
     embassies
    -0.72
    POSITIVE LOGITS
    exclusive
    1.20
    sized
    1.20
    alone
    1.04
    intensive
    1.04
    filled
    1.01
    powered
    1.00
    themed
    0.99
    fashioned
    0.97
    edged
    0.97
    centric
    0.97
    Activations Density 0.209%

    No Known Activations