© 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. 2-RES-JB
    11. 13031
    Prev
    Next
    INDEX
    Explanations

    references to a specific word - "Dam"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Dam" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.76
     Subtle
    -0.75
     Hawaiian
    -0.72
     Garner
    -0.67
     FDA
    -0.62
     Prospect
    -0.60
     Marijuana
    -0.60
    culosis
    -0.60
    chedel
    -0.60
    ģĸ
    -0.60
    POSITIVE LOGITS
    ukong
    0.96
    ned
    0.92
    iani
    0.88
    nation
    0.87
    ascus
    0.85
    iac
    0.84
    mit
    0.83
     Dam
    0.82
    essa
    0.81
    ufact
    0.81
    Activations Density 0.010%

    No Known Activations