© 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. 11046
    Prev
    Next
    INDEX
    Explanations

    references to various theories, especially those related to scientific concepts

    oai_token-act-pair · gpt-3.5-turbo

    theories and concepts related to academic disciplines and their foundational principles

    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
    BuyableInstoreAndOnline
    -0.91
    DragonMagazine
    -0.86
    Officials
    -0.80
    Lago
    -0.79
    anamo
    -0.78
    ittees
    -0.78
    staking
    -0.78
    çīĪ
    -0.76
    ittee
    -0.76
    Zone
    -0.74
    POSITIVE LOGITS
     cognition
    1.31
     causation
    1.25
     psychology
    1.22
     relativity
    1.10
     caus
    1.08
     human
    1.06
     epist
    1.05
     consciousness
    1.05
     rationality
    1.04
     computation
    1.04
    Activations Density 0.235%

    No Known Activations