© 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. 3-RES-JB
    11. 3028
    Prev
    Next
    INDEX
    Explanations

    words related to specific technical terms and keywords, possibly in a computer science or mathematical context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.81
    2200
    -0.64
     psi
    -0.60
     correctly
    -0.59
     properly
    -0.58
     homebrew
    -0.57
    hips
    -0.56
     serve
    -0.56
     anticipate
    -0.56
    elsen
    -0.56
    POSITIVE LOGITS
    oret
    1.53
    atre
    1.24
    resa
    1.23
    odore
    1.20
    ories
    1.17
    ater
    1.08
    ory
    1.00
    odor
    0.99
     earliest
    0.98
     smallest
    0.94
    Activations Density 0.136%

    No Known Activations