© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16955
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate similarity or comparison based on visual appearance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resemble" and its variations

    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
     unconditional
    -0.65
    prem
    -0.62
     upfront
    -0.62
     commitments
    -0.62
     reserves
    -0.62
     award
    -0.61
     Priority
    -0.60
     ongoing
    -0.59
     commitment
    -0.59
     pending
    -0.58
    POSITIVE LOGITS
     resemble
    3.35
     resembled
    3.03
     resembles
    3.02
     resembling
    2.56
     resemblance
    1.98
     resemb
    1.75
     reminiscent
    1.60
     imitate
    1.58
     mimic
    1.36
     emulate
    1.32
    Activations Density 0.013%

    No Known Activations