© 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. 10-RES-JB
    11. 13993
    Prev
    Next
    INDEX
    Explanations

    words related to memory recall or remembering past events

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to memory and the act of recalling past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zos
    -0.75
    roxy
    -0.72
    sterdam
    -0.70
    atri
    -0.69
    ahime
    -0.69
    atis
    -0.69
    iak
    -0.68
    assi
    -0.68
    ulhu
    -0.68
    htar
    -0.67
    POSITIVE LOGITS
     recalling
    0.91
     memories
    0.90
     vividly
    0.85
     remembering
    0.84
    remember
    0.83
     fond
    0.82
     Recall
    0.76
     recollection
    0.74
     encountering
    0.74
     accurately
    0.72
    Activations Density 0.028%

    No Known Activations