© 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. 24168
    Prev
    Next
    INDEX
    Explanations

    FIrst impressions: The neuron appears to be interested in the letter "ģ" and phrases associated with scientific and intellectual discourse

    oai_token-act-pair · gpt-3.5-turbo

    the repeated character "ģ"

    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
    raints
    -0.77
     Schr
    -0.66
     VW
    -0.64
     dialogue
    -0.63
     Sno
    -0.63
     Hunts
    -0.63
    icken
    -0.63
     Nike
    -0.62
     Euph
    -0.62
     Rapp
    -0.62
    POSITIVE LOGITS
    ģ
    1.49
    ¼
    1.20
    Ĩ
    1.14
    ¡
    1.13
    ĭ
    1.12
    Ĭ
    1.10
    µ
    1.10
    Ģ
    1.09
    ´
    1.09
    ¸
    1.08
    Activations Density 0.004%

    No Known Activations