Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3699
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems or challenges within a given context

    oai_token-act-pair · gpt-3.5-turbo

    statements about necessity or ongoing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */
    -0.74
    bilt
    -0.68
    avier
    -0.67
     caution
    -0.66
    retty
    -0.66
    loo
    -0.65
    lique
    -0.64
    #$
    -0.63
    lex
    -0.61
    RAY
    -0.61
    POSITIVE LOGITS
     plag
    0.90
     underpin
    0.81
     surround
    0.80
     hallmark
    0.76
    ģĸ
    0.68
     besie
    0.66
     emanating
    0.66
     accrued
    0.65
     engulf
    0.64
     litter
    0.63
    Activations Density 0.246%

    No Known Activations