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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14569
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pretend."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pretend" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srf
    -0.69
    ccording
    -0.67
    âĨij
    -0.64
    cutting
    -0.62
    APH
    -0.61
    vez
    -0.60
    hani
    -0.59
    chains
    -0.59
    lean
    -0.59
    hner
    -0.59
    POSITIVE LOGITS
     innocence
    0.78
    ulence
    0.77
    entious
    0.74
     forgot
    0.70
    orial
    0.65
     Moose
    0.64
    ishly
    0.64
    zel
    0.63
    ensions
    0.63
    plane
    0.62
    Activations Density 0.016%

    No Known Activations