© 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. 16825
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific word, "lasagna," across different contexts or subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to the name 'AGA' and its variations within contexts

    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
    ership
    -0.69
     contributors
    -0.66
     observable
    -0.61
     present
    -0.60
     pse
    -0.60
     AAP
    -0.60
     demonstr
    -0.58
     WHO
    -0.57
    uple
    -0.57
     tolerated
    -0.57
    POSITIVE LOGITS
    aga
    1.29
    ña
    1.00
    ption
    1.00
    amaz
    0.86
     Siren
    0.86
    oka
    0.84
    qua
    0.80
    estro
    0.79
    velength
    0.78
    vernment
    0.77
    Activations Density 0.006%

    No Known Activations