© 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. 10-RES-JB
    11. 9957
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or companies and the year they were founded

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "founded" and related terms signifying the creation of organizations or ventures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dstg
    -0.91
     slightest
    -0.70
    Elsa
    -0.69
    achy
    -0.68
    anyl
    -0.68
    âĨij
    -0.67
    Putin
    -0.67
    enery
    -0.65
    same
    -0.65
    Asked
    -0.64
    POSITIVE LOGITS
     Operation
    0.92
     Habit
    0.84
     Know
    0.82
     Bound
    0.80
     Pulse
    0.78
     Drift
    0.76
     Alternative
    0.76
     Project
    0.75
     www
    0.75
     Cod
    0.75
    Activations Density 0.196%

    No Known Activations