© 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. 23546
    Prev
    Next
    INDEX
    Explanations

    instances of the word "self" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "self" and its variations

    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
     Appropriations
    -0.72
     CES
    -0.72
     Sierra
    -0.66
     Viet
    -0.63
     Flavoring
    -0.62
     footsteps
    -0.62
     seasoning
    -0.61
     Amend
    -0.60
     ounces
    -0.59
     AST
    -0.59
    POSITIVE LOGITS
    destruct
    1.11
    self
    1.10
    selves
    1.04
     destruct
    1.01
    ortium
    0.83
    claimed
    0.76
    finder
    0.76
    ridges
    0.75
    upload
    0.73
    lect
    0.72
    Activations Density 0.005%

    No Known Activations