© 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. 1-RES-JB
    11. 24183
    Prev
    Next
    INDEX
    Explanations

    the word "amy" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Amy" and its variations, demonstrating a focus on individuals with this name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.68
     Wizard
    -0.68
    Lt
    -0.66
    ^^^^
    -0.66
     Wonder
    -0.65
     totality
    -0.65
     FEMA
    -0.63
     Gree
    -0.63
     Ranger
    -0.62
     Lt
    -0.61
    POSITIVE LOGITS
    gdala
    1.52
    amy
    1.51
    amous
    1.03
    ony
    0.97
    phal
    0.92
    amia
    0.91
    odo
    0.90
    antic
    0.89
    arov
    0.89
    acy
    0.87
    Activations Density 0.005%

    No Known Activations