© 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. 1-RES-JB
    11. 12856
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing support or boosting something

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs or verb forms that suggest an action has been completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JUST
    -0.65
    æĥ
    -0.64
     Antar
    -0.63
    Balt
    -0.62
    åī
    -0.62
    女
    -0.61
    é¾įåĸļ士
    -0.59
    izen
    -0.59
    æ°
    -0.59
    ä»
    -0.58
    POSITIVE LOGITS
    pped
    1.19
    olicy
    1.06
    pping
    1.06
    berra
    0.96
    terday
    0.93
    ulously
    0.86
    avascript
    0.83
    hap
    0.83
    ocalyptic
    0.81
    undown
    0.81
    Activations Density 0.007%

    No Known Activations