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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 7247
    Prev
    Next
    INDEX
    Explanations

    words related to legal charges and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    counts of legal charges and offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     goodbye
    -0.72
    flush
    -0.65
     congr
    -0.65
     fri
    -0.65
    opian
    -0.64
     ze
    -0.64
    Soft
    -0.63
     valleys
    -0.63
    nas
    -0.63
     Jagu
    -0.61
    POSITIVE LOGITS
     felony
    1.51
     misdemeanor
    1.47
     counts
    1.47
     misdem
    1.41
     fel
    1.22
     charges
    1.19
     offenses
    1.18
     count
    1.13
     aggravated
    1.11
     offences
    1.09
    Activations Density 0.122%

    No Known Activations