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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 12096
    Prev
    Next
    INDEX
    Explanations

    phrases related to forensic evidence

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with forensic analysis

    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
    unin
    -0.97
    yip
    -0.87
     Huck
    -0.71
    Spoiler
    -0.67
    rir
    -0.66
    rish
    -0.65
    iah
    -0.64
    cair
    -0.63
    ammy
    -0.63
    Reilly
    -0.63
    POSITIVE LOGITS
    nsic
    1.02
    nsics
    0.91
    abilia
    0.89
     examination
    0.84
     analysis
    0.80
     pathology
    0.76
    alyses
    0.76
     biologist
    0.75
     forensic
    0.75
     examinations
    0.75
    Activations Density 0.013%

    No Known Activations