© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1166
    Prev
    Next
    INDEX
    Explanations

    mentions of strong positive emotions related to personal memories or experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fondness related to memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irrel
    -0.71
    DoS
    -0.67
    udder
    -0.67
    ulhu
    -0.65
    aminer
    -0.64
     helicop
    -0.64
    adesh
    -0.64
     DOWN
    -0.64
    pta
    -0.63
    IVER
    -0.63
    POSITIVE LOGITS
     fond
    1.10
    uously
    0.93
     memories
    0.91
    est
    0.88
    iously
    0.88
    entimes
    0.87
    ties
    0.86
    ness
    0.85
     Memories
    0.83
    algia
    0.83
    Activations Density 0.020%

    No Known Activations