© 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. 6-RES-JB
    11. 3807
    Prev
    Next
    INDEX
    Explanations

    names or words ending in 'ler'

    oai_token-act-pair · gpt-3.5-turbo

    the word "ler" 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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADRA
    -0.73
    raints
    -0.69
    popular
    -0.66
    SIM
    -0.61
    ouls
    -0.61
    ĸļ
    -0.61
    ulating
    -0.59
    ulet
    -0.58
    liest
    -0.58
    abis
    -0.58
    POSITIVE LOGITS
    oad
    0.97
    gren
    0.93
    istics
    0.93
    ibrary
    0.88
    iffe
    0.87
    ogue
    0.87
    oaded
    0.80
    gage
    0.77
    anguage
    0.76
    sonian
    0.75
    Activations Density 0.025%

    No Known Activations