Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 15015
    Prev
    Next
    INDEX
    Explanations

    instances related to education or instruction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "educate" and its variations

    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
    oter
    -0.74
    aws
    -0.71
    eda
    -0.66
    abba
    -0.65
     Species
    -0.63
    ntax
    -0.62
    itual
    -0.62
    thus
    -0.60
    orr
    -0.60
    oner
    -0.59
    POSITIVE LOGITS
     educate
    1.04
    Educ
    0.85
    ¿½
    0.85
     educating
    0.83
     educ
    0.81
    tackle
    0.80
     IPS
    0.79
    ments
    0.78
    ItemImage
    0.77
    urally
    0.77
    Activations Density 0.013%

    No Known Activations