© 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. 16561
    Prev
    Next
    INDEX
    Explanations

    the word "sort" occurring with varying strengths of match

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sort" used to categorize or describe things

    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
    PLIC
    -0.65
    ULTS
    -0.64
    HAEL
    -0.62
     Dent
    -0.62
    interrupted
    -0.61
     Madison
    -0.59
    UNCH
    -0.59
    OPER
    -0.58
    NZ
    -0.58
    PLIED
    -0.58
    POSITIVE LOGITS
    liness
    0.85
    entially
    0.80
    oscope
    0.78
    ãĤ¦ãĤ¹
    0.77
    ilege
    0.77
    ative
    0.77
    ies
    0.76
    ically
    0.74
    ie
    0.74
    abouts
    0.73
    Activations Density 0.039%

    No Known Activations