© 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. 12653
    Prev
    Next
    INDEX
    Explanations

    terms related to specific viewpoints or ideologies, particularly focusing on the suffix "-ist."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various ideologies, particularly those ending in 'ist'

    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
    ecause
    -0.78
    perty
    -0.68
    ilings
    -0.67
    sembly
    -0.67
    accompanied
    -0.67
    BOX
    -0.66
     speedy
    -0.66
    tesy
    -0.66
    upon
    -0.66
     smoot
    -0.64
    POSITIVE LOGITS
    ess
    0.93
    geist
    0.85
     extraord
    0.85
    ãĤº
    0.80
    opol
    0.77
    otle
    0.75
     tendencies
    0.75
    essed
    0.72
    rior
    0.72
    ophe
    0.71
    Activations Density 0.027%

    No Known Activations