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

    Neuronpedia

    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. 5138
    Prev
    Next
    INDEX
    Explanations

    noun phrases related to possession, control, or personal attributes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and personal identification issues

    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
    >)
    -0.74
    inks
    -0.68
    ares
    -0.66
    etheless
    -0.65
    arling
    -0.64
    orry
    -0.62
    wy
    -0.62
    Avg
    -0.62
    othing
    -0.61
    âĸĪâĸĪâĸĪâĸĪ
    -0.60
    POSITIVE LOGITS
     removed
    1.33
     erased
    1.27
     revoked
    1.20
     reinstated
    1.19
     taken
    1.16
     overturned
    1.15
     scrapped
    1.15
     undone
    1.15
     examined
    1.14
     dismantled
    1.14
    Activations Density 0.368%

    No Known Activations