© 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. 9-RES-JB
    6. 5447
    Prev
    Next
    INDEX
    Explanations

    phrases or words ending in "ij"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to individuals or entities, particularly in a context highlighting their actions or attributes

    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
     interchangeable
    -0.64
    ACTED
    -0.64
     poppy
    -0.61
     equally
    -0.60
     flushed
    -0.60
     bleach
    -0.59
     flush
    -0.58
    女
    -0.57
     flux
    -0.57
     Kubrick
    -0.57
    POSITIVE LOGITS
    ournal
    1.29
    eh
    1.19
    utsu
    1.01
    oji
    0.91
    ean
    0.91
    ecause
    0.91
    uu
    0.90
    ohn
    0.90
    inx
    0.87
    unction
    0.86
    Activations Density 0.032%

    No Known Activations