© 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. 2-RES-JB
    11. 7753
    Prev
    Next
    INDEX
    Explanations

    words related to technology and chemical compounds with 'xt' in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "xt" and its variations, indicating a focus on specific programming or notation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -1.08
    Downloadha
    -0.99
    TPPStreamerBot
    -0.84
    BRE
    -0.82
    NetMessage
    -0.76
    UGH
    -0.76
    é¾įåĸļ士
    -0.73
    GROUND
    -0.71
     Converted
    -0.67
    inventoryQuantity
    -0.66
    POSITIVE LOGITS
    ensions
    1.26
    reme
    1.25
    ension
    1.17
    ract
    1.12
    uple
    1.04
    racted
    1.02
    ended
    1.01
    inent
    1.00
    ractor
    0.98
    raph
    0.94
    Activations Density 0.006%

    No Known Activations