INDEX

Explanations

mentions of government decisions and actions related to policies and laws

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tert

-0.70

mbuds

-0.64

agog

-0.63

ordinate

-0.63

 adulthood

-0.61

 denomin

-0.60

 ancest

-0.59

 resid

-0.58

 certific

-0.58

 nanop

-0.58

POSITIVE LOGITS

 spree

0.95

 involving

0.84

nings

0.81

fulness

0.77

backs

0.76

athon

0.74

 aimed

0.74

 announcement

0.74

lessness

0.70

âĶĢâĶĢ

0.70

Activations Density 3.185%

mentions of government decisions and actions related to policies and laws

No Comments

No Known Activations