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. 4-RES-JB
    6. 8465
    Prev
    Next
    INDEX
    Explanations

    the name "Alison" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ison" in various contexts, indicating a focus on individuals or entities related to that term

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

    No Comments

    Negative Logits
    appers
    -0.83
    uled
    -0.77
     cryst
    -0.77
    undo
    -0.76
    astically
    -0.74
    izoph
    -0.70
    ulative
    -0.69
     therape
    -0.68
     cryptoc
    -0.68
     exha
    -0.67
    POSITIVE LOGITS
    naire
    0.91
    ette
    0.90
    ison
    0.88
    xual
    0.85
    nect
    0.85
    ettes
    0.84
    xes
    0.83
    ements
    0.83
    nette
    0.83
    hof
    0.82
    Activations Density 0.012%

    No Known Activations