© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14973
    Prev
    Next
    INDEX
    Explanations

    phrases related to thorough investigations or detailed examinations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "extensive" and related terms indicating thoroughness or detail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enos
    -0.77
    hops
    -0.73
    earth
    -0.71
    corn
    -0.71
    igg
    -0.71
    leader
    -0.71
    sticks
    -0.70
    warm
    -0.70
    hop
    -0.70
    ques
    -0.69
    POSITIVE LOGITS
    bred
    0.93
     examination
    0.93
     interrogation
    0.84
     disse
    0.83
     overview
    0.83
     customization
    0.82
     documentation
    0.81
     examinations
    0.81
     profiling
    0.81
     renovations
    0.80
    Activations Density 0.045%

    No Known Activations