© 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. 9-RES-JB
    11. 8687
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "prototype" or words similar to "prototype" such as "prot", "prototypes", "protagonist", and "protection"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prototypes and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.89
    è£ħ
    -0.76
    upon
    -0.69
    INESS
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    forth
    -0.65
     McGee
    -0.65
    çĽ
    -0.64
     mund
    -0.64
    çĶ°
    -0.63
    POSITIVE LOGITS
    ected
    1.45
    otyp
    1.37
    agonist
    1.35
    otypes
    1.31
    ests
    1.30
    racted
    1.27
    ractor
    1.27
    ector
    1.20
    agonists
    1.20
    ocol
    1.19
    Activations Density 0.046%

    No Known Activations