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. 7206
    Prev
    Next
    INDEX
    Explanations

    phrases related to exposure or being exposed to something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "exposed" related to various contexts or risks

    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
    ylum
    -0.84
    widget
    -0.77
    translation
    -0.68
    driver
    -0.67
    notations
    -0.66
    signed
    -0.66
    rollers
    -0.66
    tenance
    -0.64
    employed
    -0.64
    swers
    -0.64
    POSITIVE LOGITS
     radiation
    0.85
     fend
    0.84
     acid
    0.83
     fire
    0.81
    othy
    0.78
     sunlight
    0.76
     acids
    0.76
     gunfire
    0.74
     ozone
    0.73
    asted
    0.73
    Activations Density 0.077%

    No Known Activations