© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9517
    Prev
    Next
    INDEX
    Explanations

    words related to self, such as self-supporting, self-medicated, self-defense, self-esteem, and self-employed

    oai_token-act-pair · gpt-3.5-turbo

    references to self-related concepts

    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
     Flavoring
    -0.84
     GOODMAN
    -0.82
     Slay
    -0.82
     Amend
    -0.77
     Fever
    -0.71
    IUM
    -0.70
     Cosponsors
    -0.68
     Syndicate
    -0.66
     Sierra
    -0.65
     Orchestra
    -0.65
    POSITIVE LOGITS
    destruct
    1.13
     destruct
    1.07
     self
    1.02
    upload
    0.89
    self
    0.87
    Self
    0.84
     diseng
    0.84
    lect
    0.78
     explanatory
    0.78
    aram
    0.77
    Activations Density 0.016%

    No Known Activations