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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16944
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds or scientific processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the chemical and biological composition of substances

    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
    BIP
    -0.77
    TPPStreamerBot
    -0.74
    CVE
    -0.71
    Reviewer
    -0.70
     sanctions
    -0.65
     behavi
    -0.61
     appropriation
    -0.61
     resemb
    -0.60
     ceiling
    -0.60
     similarities
    -0.59
    POSITIVE LOGITS
    ensions
    1.15
    reme
    1.13
    uple
    1.09
    racted
    1.04
    ension
    1.01
    ortion
    0.99
    rot
    0.99
    ract
    0.98
    rous
    0.96
    ropy
    0.94
    Activations Density 0.039%

    No Known Activations