© 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. 1-RES-JB
    11. 20988
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'loner'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "loner" and similar terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ward
    -0.70
     Sherman
    -0.63
    MAP
    -0.62
    Ka
    -0.61
    eq
    -0.60
    å°Ĩ
    -0.60
    MED
    -0.60
     Globe
    -0.58
    Tex
    -0.58
     Butterfly
    -0.58
    POSITIVE LOGITS
    oner
    1.55
     confir
    1.05
    etheless
    0.86
     extraord
    0.85
     unden
    0.84
    getic
    0.83
     enthusi
    0.83
    \\\\
    0.82
    geon
    0.82
     psychiat
    0.81
    Activations Density 0.007%

    No Known Activations