© 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. 7-RES-JB
    11. 22916
    Prev
    Next
    INDEX
    Explanations

    memories or sentiments associated with positive emotions and personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of nostalgia or fondness towards memories and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.71
    irrel
    -0.71
    ulhu
    -0.70
    FT
    -0.66
    IPP
    -0.66
    asar
    -0.64
    DoS
    -0.64
    iphate
    -0.62
    utherford
    -0.62
    IVER
    -0.62
    POSITIVE LOGITS
     fond
    1.08
     memories
    1.03
     remem
    0.92
    ties
    0.90
    rish
    0.90
     Memories
    0.88
    est
    0.88
    uously
    0.87
    ries
    0.87
    iously
    0.86
    Activations Density 0.051%

    No Known Activations