Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9108
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent events involving victims being harmed or injured

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" and its variations in different contexts

    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
     Countries
    -0.81
    isites
    -0.78
     Extend
    -0.78
     Requirements
    -0.73
    isite
    -0.73
     Critics
    -0.72
     Costs
    -0.71
     Taxes
    -0.68
    inav
    -0.68
     aspire
    -0.67
    POSITIVE LOGITS
     hospitalized
    1.35
     stabbed
    1.19
     arrested
    1.16
     transported
    1.15
     assaulted
    1.14
     asleep
    1.12
     fatally
    1.12
     evacuated
    1.11
     bitten
    1.09
     killed
    1.07
    Activations Density 0.134%

    No Known Activations