Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6790
    Prev
    Next
    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    " a" following a name & comma, eg "John Smith, a"

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eye
    -0.73
    EXP
    -0.72
    iosity
    -0.72
    Episode
    -0.72
    Operation
    -0.69
     asses
    -0.69
    wcsstore
    -0.67
    EMA
    -0.66
    Untitled
    -0.64
     Intent
    -0.64
    POSITIVE LOGITS
     spokesman
    1.21
     spokesperson
    1.16
     lecturer
    1.15
     longtime
    1.12
     spokeswoman
    1.11
     professor
    1.08
     member
    1.07
     lawyer
    1.06
     former
    1.04
     retired
    1.04
    Activations Density 0.073%

    No Known Activations