© 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. 14250
    Prev
    Next
    INDEX
    Explanations

    mentions of state-related topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to state-funded entities and issues

    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
     beads
    -0.77
     Candle
    -0.76
     Arrows
    -0.72
     Voy
    -0.69
     Blades
    -0.69
     Hobbit
    -0.68
     Creator
    -0.68
     paddle
    -0.67
     Mek
    -0.65
     Connie
    -0.64
    POSITIVE LOGITS
    sponsored
    1.50
    funded
    1.47
    backed
    1.45
    controlled
    1.42
    issued
    1.42
    approved
    1.38
    appointed
    1.37
    owned
    1.32
    supported
    1.29
    imposed
    1.24
    Activations Density 0.047%

    No Known Activations