© 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. 4-RES-JB
    11. 11173
    Prev
    Next
    INDEX
    Explanations

    phrases indicating being in a situation or opinion shared by others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "not alone" or variations indicating a state of loneliness or lack of solitude

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

    No Comments

    Negative Logits
    nant
    -0.82
    emies
    -0.74
    inders
    -0.74
    imum
    -0.67
    imal
    -0.66
    mosp
    -0.64
    aptic
    -0.63
    emy
    -0.62
    MER
    -0.62
    umm
    -0.60
    POSITIVE LOGITS
     anymore
    0.70
    PsyNetMessage
    0.69
     unaccompanied
    0.66
    lihood
    0.64
     respons
    0.62
     isolated
    0.62
    angelo
    0.62
    ––
    0.60
     consolation
    0.59
     altru
    0.59
    Activations Density 0.006%

    No Known Activations