© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14381
    Prev
    Next
    INDEX
    Explanations

    references to actions taken or events that have occurred

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     territ
    -0.63
    catentry
    -0.63
    ocol
    -0.60
     colonization
    -0.60
     Apart
    -0.59
    housing
    -0.58
     fireball
    -0.55
     settlement
    -0.54
     blending
    -0.54
     neigh
    -0.53
    POSITIVE LOGITS
     been
    1.22
    been
    1.04
     Been
    0.96
     undergone
    0.93
    gotten
    0.92
     gotten
    0.92
     taken
    0.85
    ĸļ
    0.85
     gone
    0.84
     done
    0.82
    Activations Density 0.242%

    No Known Activations