© 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. 7-RES-JB
    11. 2097
    Prev
    Next
    INDEX
    Explanations

    instances when something is made clear or obvious from a description or situation

    oai_token-act-pair · gpt-3.5-turbo

    the word "from" to indicate sources or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nets
    -0.72
    imes
    -0.72
    mouth
    -0.71
    bush
    -0.71
    isode
    -0.70
    idy
    -0.70
    illus
    -0.69
    icer
    -0.68
    icide
    -0.67
    busters
    -0.67
    POSITIVE LOGITS
     afar
    1.75
     whence
    1.15
     scratch
    1.04
     outset
    0.99
     thence
    0.95
     inside
    0.92
     standpoint
    0.92
     nowhere
    0.91
     within
    0.90
     elsewhere
    0.89
    Activations Density 0.121%

    No Known Activations