© 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. 10-RES-JB
    11. 2663
    Prev
    Next
    INDEX
    Explanations

    names or pronouns referring to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.82
    animate
    -0.64
     murderer
    -0.64
    Load
    -0.62
    UTE
    -0.62
     lifes
    -0.61
    «ĺ
    -0.60
     transformative
    -0.60
     Nirvana
    -0.60
    ¾
    -0.59
    POSITIVE LOGITS
     intends
    1.65
     expects
    1.63
     hopes
    1.55
     wants
    1.49
     anticip
    1.46
     insists
    1.46
     believes
    1.45
     prefers
    1.43
     vows
    1.37
     proposes
    1.30
    Activations Density 0.426%

    No Known Activations