© 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. 16485
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to a person's period of holding a particular position or job

    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
    glers
    -0.61
    abel
    -0.61
     Detect
    -0.60
    izer
    -0.59
    Girl
    -0.58
     Ingredients
    -0.58
     Piercing
    -0.57
     Doll
    -0.57
    hew
    -0.57
    FIG
    -0.57
    POSITIVE LOGITS
     tenure
    3.83
     stint
    1.18
     tenancy
    1.17
     reign
    1.10
     managerial
    1.06
     career
    1.04
     appointment
    1.02
     patronage
    1.01
     stature
    1.01
     lifespan
    1.00
    Activations Density 0.014%

    No Known Activations