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. 19041
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court outcomes like acquittal and exoneration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal acquittals and exonerations

    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
    hare
    -0.77
    CRE
    -0.75
     anx
    -0.71
    UNCH
    -0.69
    ertility
    -0.68
    KEY
    -0.66
    layout
    -0.66
     outage
    -0.65
    incinn
    -0.63
    oper
    -0.63
    POSITIVE LOGITS
     verdict
    0.95
     indict
    0.89
     exoner
    0.89
     Prosecutors
    0.86
     innocence
    0.85
    ittal
    0.84
     convict
    0.83
     manslaughter
    0.80
     wrongdoing
    0.80
     Prosecutor
    0.80
    Activations Density 0.053%

    No Known Activations