© 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 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. 3347
    Prev
    Next
    INDEX
    Explanations

    words related to memory processes and cognitive functions

    oai_token-act-pair · gpt-3.5-turbo

    concepts associated with memory and cognitive processing

    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
    ©¶æ¥µ
    -0.86
    BSD
    -0.79
     Cowboy
    -0.77
    Engine
    -0.76
     Sov
    -0.75
     Engineers
    -0.74
     Punk
    -0.72
     Asylum
    -0.71
    Shut
    -0.68
     Engineering
    -0.68
    POSITIVE LOGITS
     stimuli
    1.84
     stimulus
    1.45
     cues
    1.45
     salient
    1.32
     cue
    1.25
     sensory
    1.12
     objects
    1.10
    versive
    1.10
     perceptual
    1.04
     unfamiliar
    1.02
    Activations Density 0.397%

    No Known Activations