© 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. 11-RES-JB
    11. 10272
    Prev
    Next
    INDEX
    Explanations

    phrases related to encountering or discovering something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "come" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.80
    popular
    -0.59
     Editors
    -0.58
     pens
    -0.58
    wings
    -0.57
    assert
    -0.57
     Turtles
    -0.57
    blogspot
    -0.57
     Whoever
    -0.57
     Genie
    -0.56
    POSITIVE LOGITS
     across
    1.10
     upon
    1.08
     encountering
    1.03
     face
    0.85
     faced
    0.85
     encounter
    0.81
     confronted
    0.79
    Across
    0.79
     peril
    0.77
     home
    0.76
    Activations Density 0.106%

    No Known Activations