© 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
    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. 24193
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "ble"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ble."

    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
    ancial
    -0.70
    doms
    -0.69
    erva
    -0.68
     Ernst
    -0.68
    ahime
    -0.67
    ammad
    -0.65
    ellar
    -0.65
    AMI
    -0.64
     ACTIONS
    -0.62
    alli
    -0.62
    POSITIVE LOGITS
    ble
    1.31
    bles
    1.31
    bled
    1.02
    bling
    1.01
    bly
    0.94
    tt
    0.81
    bum
    0.80
    ede
    0.77
    vous
    0.77
    ogle
    0.76
    Activations Density 0.007%

    No Known Activations