© 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. 12704
    Prev
    Next
    INDEX
    Explanations

    phrases related to exceeding boundaries or limits

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "step."

    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
    binding
    -0.66
    gdala
    -0.65
     Blueprint
    -0.64
    OUNT
    -0.63
     eleph
    -0.62
     Corpus
    -0.62
     totality
    -0.60
     Psycho
    -0.60
     Io
    -0.60
    inatory
    -0.59
    POSITIVE LOGITS
    ste
    1.25
    chnology
    1.01
    lla
    0.88
    chn
    0.86
    Ste
    0.84
    pping
    0.83
    ering
    0.82
    arde
    0.82
    eling
    0.81
    alth
    0.81
    Activations Density 0.005%

    No Known Activations