© 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. 10-RES-JB
    11. 14170
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of self

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating self-reference or self-descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUM
    -0.78
    ICAN
    -0.78
     Ashe
    -0.77
     XIII
    -0.70
    ONT
    -0.69
    etter
    -0.68
    rium
    -0.68
    oice
    -0.65
    oric
    -0.65
    IENCE
    -0.64
    POSITIVE LOGITS
    destruct
    1.11
    lessly
    1.05
    -
    1.01
    same
    1.01
     destruct
    0.93
     explanatory
    0.93
    proclaimed
    0.92
    ridges
    0.89
    âĢij
    0.88
    less
    0.86
    Activations Density 0.016%

    No Known Activations