© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 22929
    Prev
    Next
    INDEX
    Explanations

    personal experiences or actions described in the first person

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "I" and related personal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loops
    -0.69
     decoration
    -0.68
     Haku
    -0.66
     dies
    -0.63
     2048
    -0.62
    INGTON
    -0.62
     stagnation
    -0.61
     Ezekiel
    -0.59
    Ĥİ
    -0.59
     reversible
    -0.58
    POSITIVE LOGITS
    ldon
    0.99
    xtap
    0.92
    ñ
    0.87
    cade
    0.80
    emen
    0.80
    adr
    0.80
    opia
    0.79
    aci
    0.79
    arag
    0.79
    atri
    0.78
    Activations Density 0.322%

    No Known Activations