© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 23295
    Prev
    Next
    INDEX
    Explanations

    words or parts of words with the sequence 'ese'

    oai_token-act-pair · gpt-3.5-turbo

    word endings that indicate a certain kind of language or dialect, particularly those that imply a regional linguistic feature

    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
     Cumm
    -0.71
    SAN
    -0.71
    rost
    -0.67
    rid
    -0.67
    razil
    -0.65
    Scotland
    -0.65
    AMI
    -0.64
     Humanity
    -0.64
    ific
    -0.63
    Allen
    -0.62
    POSITIVE LOGITS
    ese
    1.07
    soever
    0.81
    uth
    0.78
    chuk
    0.78
    agues
    0.78
    asus
    0.76
    ema
    0.75
    ased
    0.75
    zzo
    0.75
    urry
    0.74
    Activations Density 0.009%

    No Known Activations