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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 238
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking and delivering justice

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to justice and accountability

    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
     Supplement
    -0.82
     pse
    -0.71
     Sturgeon
    -0.70
    acly
    -0.69
    alg
    -0.65
    imester
    -0.61
    NetMessage
    -0.61
     Echoes
    -0.61
     Digest
    -0.60
     Flex
    -0.60
    POSITIVE LOGITS
     punished
    1.49
     prosecuted
    1.36
     accountable
    1.29
     jailed
    1.27
     apprehended
    1.19
     indicted
    1.16
     arrested
    1.15
     justice
    1.14
     imprisoned
    1.13
     repent
    1.12
    Activations Density 0.334%

    No Known Activations