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. 5569
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology and companies, as well as mentions of physical medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'T' in various contexts

    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
     persisted
    -0.69
    ellar
    -0.66
     recess
    -0.61
     flock
    -0.59
     divided
    -0.58
    manship
    -0.57
     deliberate
    -0.57
     confinement
    -0.56
     peas
    -0.56
     persist
    -0.56
    POSITIVE LOGITS
    T
    3.29
    Ts
    2.41
    TG
    1.76
    TED
    1.67
     T
    1.67
    Ti
    1.64
    t
    1.64
    TING
    1.62
    TN
    1.62
    TT
    1.58
    Activations Density 0.027%

    No Known Activations