INDEX

Explanations

scientific and medical terms related to biology, neuroscience, psychology, and anatomy

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fires

-0.70

eless

-0.70

etime

-0.70

engers

-0.69

inel

-0.68

estead

-0.67

ership

-0.67

inki

-0.66

ishers

-0.66

leased

-0.66

POSITIVE LOGITS

 textbooks

1.13

 professor

1.03

utics

0.93

ology

0.87

 professors

0.86

 lecturer

0.86

 textbook

0.86

istry

0.82

PhD

0.81

 sciences

0.79

Activations Density 0.084%

scientific and medical terms related to biology, neuroscience, psychology, and anatomy

No Comments

No Known Activations