© 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. 4-RES-JB
    11. 19648
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that are followed by a verb indicating a change or action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "turned" in various contexts

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

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.95
    capacity
    -0.75
    inately
    -0.74
    icipated
    -0.73
    foundation
    -0.73
    oids
    -0.72
     Reasons
    -0.70
    hart
    -0.67
    Story
    -0.67
    llah
    -0.67
    POSITIVE LOGITS
    terday
    0.70
    agra
    0.68
     into
    0.68
     shif
    0.66
     inward
    0.66
    about
    0.65
     invisible
    0.65
     toward
    0.64
    bum
    0.64
    ends
    0.63
    Activations Density 0.033%

    No Known Activations