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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17328
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal sentences and crime

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal sentences and penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.90
    NetMessage
    -0.73
    INC
    -0.69
     Alic
    -0.68
    ãĤ¤ãĥĪ
    -0.67
    sie
    -0.67
    orp
    -0.66
     Klu
    -0.66
    erial
    -0.66
    earth
    -0.66
    POSITIVE LOGITS
     imprisonment
    1.02
     imposed
    0.95
     sentences
    0.94
     incarceration
    0.92
    ishment
    0.88
     sentence
    0.88
     detention
    0.87
     incarcerated
    0.87
     inflicted
    0.86
     awarded
    0.86
    Activations Density 0.071%

    No Known Activations