© 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. 2-RES-JB
    11. 12619
    Prev
    Next
    INDEX
    Explanations

    terms related to forceful actions or compression

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "ram" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Johns
    -0.72
     Vald
    -0.69
     Knight
    -0.67
    NC
    -0.67
     Marqu
    -0.66
     Darkness
    -0.66
     Clo
    -0.65
    KI
    -0.65
     Jenner
    -0.65
     Wid
    -0.65
    POSITIVE LOGITS
     ram
    1.26
    ming
    1.11
    dump
    1.03
    disk
    0.98
    irez
    0.97
    pling
    0.90
    rod
    0.90
    bling
    0.86
    ram
    0.82
    pled
    0.80
    Activations Density 0.008%

    No Known Activations