© 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. 0-RES-JB
    11. 13082
    Prev
    Next
    INDEX
    Explanations

    locations or places where entities are situated or accommodated

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "housed" and related concepts of accommodation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     replay
    -0.64
    Quote
    -0.62
     prediction
    -0.61
    oes
    -0.60
     League
    -0.60
     Summoner
    -0.60
     predictions
    -0.59
     autop
    -0.59
     contribution
    -0.59
    eely
    -0.58
    POSITIVE LOGITS
     housed
    3.76
     situated
    1.26
     comprised
    1.24
     accommod
    1.21
     resided
    1.20
     contained
    1.19
     located
    1.18
    Located
    1.17
     tucked
    1.16
     lodged
    1.15
    Activations Density 0.023%

    No Known Activations