© 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. 0-RES-JB
    11. 16422
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to oneself

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flags
    -0.63
     recycled
    -0.62
     reused
    -0.61
     stripes
    -0.60
     Scarlet
    -0.60
     Flags
    -0.59
     brackets
    -0.59
     instances
    -0.59
     primitive
    -0.58
     franchises
    -0.57
    POSITIVE LOGITS
    me
    4.23
    mes
    2.17
    ME
    2.05
    Me
    1.92
     ME
    1.49
    med
    1.48
     Me
    1.45
    mine
    1.45
    my
    1.40
    ming
    1.37
    Activations Density 0.012%

    No Known Activations