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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 11072
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to autism

    oai_token-act-pair · gpt-3.5-turbo

    references to autism and related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tar
    -0.76
    wer
    -0.66
     Pas
    -0.64
     Petro
    -0.63
    ixtures
    -0.63
    WC
    -0.63
     fres
    -0.62
    zb
    -0.62
    Disk
    -0.62
     Steal
    -0.62
    POSITIVE LOGITS
     autism
    3.81
     Autism
    3.15
     autistic
    2.77
     ASD
    2.11
     schizophrenia
    1.79
     ADHD
    1.78
     measles
    1.59
     epilepsy
    1.58
     asthma
    1.49
     polio
    1.48
    Activations Density 0.028%

    No Known Activations