© 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. 12301
    Prev
    Next
    INDEX
    Explanations

    information related to personal details and backgrounds, such as birthplaces and family backgrounds

    oai_token-act-pair · gpt-3.5-turbo

    biographical details about individuals, including their place and date of birth

    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
    mbuds
    -0.90
     takedown
    -0.81
     Solitaire
    -0.79
     Reloaded
    -0.74
    ħĭ
    -0.72
    threat
    -0.71
    anity
    -0.71
     deterrence
    -0.70
    ĸļ
    -0.69
    Alert
    -0.69
    POSITIVE LOGITS
     upbringing
    1.38
     grew
    1.20
     childhood
    1.12
     educated
    1.07
     schooling
    1.04
     maternal
    1.01
     eldest
    1.01
     graduated
    1.00
     earliest
    0.99
     adolescence
    0.99
    Activations Density 0.326%

    No Known Activations