© 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. 0-RES-JB
    11. 2929
    Prev
    Next
    INDEX
    Explanations

    entities or individuals residing or located in specific places

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of residence or living in a particular place

    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
     tense
    -0.80
     Pitch
    -0.70
     Nato
    -0.67
     quick
    -0.64
     Reaction
    -0.63
     dramatic
    -0.60
     Simon
    -0.59
     stra
    -0.59
     Casual
    -0.58
     pitch
    -0.57
    POSITIVE LOGITS
     reside
    3.39
     resides
    3.33
     resided
    3.01
     residing
    2.39
     inhabit
    1.40
     originate
    1.35
     residence
    1.20
     belongs
    1.18
     roam
    1.18
     belonged
    1.16
    Activations Density 0.028%

    No Known Activations