© 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. 1-RES-JB
    11. 16832
    Prev
    Next
    INDEX
    Explanations

    the word "achi"

    oai_token-act-pair · gpt-3.5-turbo

    names or variations of names associated with people, likely in a journalistic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.64
    perse
    -0.62
    runs
    -0.60
    display
    -0.60
    Aut
    -0.58
    IAL
    -0.58
     mileage
    -0.58
     tread
    -0.58
    lining
    -0.58
    elling
    -0.58
    POSITIVE LOGITS
    achi
    1.68
    ubi
    0.88
    ibi
    0.87
    aii
    0.84
    uble
    0.84
    iba
    0.82
    uchi
    0.81
    ushi
    0.80
    velength
    0.79
    anty
    0.79
    Activations Density 0.003%

    No Known Activations