© 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. 15647
    Prev
    Next
    INDEX
    Explanations

    words related to changes such as declines, falls, rises, and drops in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decreases or declines in various contexts

    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
     extras
    -0.65
     vandal
    -0.64
    rich
    -0.63
     Exile
    -0.62
    flix
    -0.60
    racuse
    -0.58
     quir
    -0.57
     exile
    -0.56
     subtitles
    -0.56
     Voc
    -0.55
    POSITIVE LOGITS
     rate
    0.93
    ait
    0.86
     occurring
    0.84
     rates
    0.83
     wrought
    0.81
    lust
    0.81
    luster
    0.78
    ghai
    0.78
     coincided
    0.76
     between
    0.75
    Activations Density 0.197%

    No Known Activations