INDEX

Explanations

terms related to economic and political discussions

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

—"

-0.69

kamp

-0.65

dies

-0.62

-"

-0.61

eff

-0.61

rift

-0.61

duct

-0.60

Ó

-0.59

retch

-0.58

ËĪ

-0.58

POSITIVE LOGITS

 importantly

0.95

withstanding

0.94

Ago

0.91

ortunately

0.86

etheless

0.85

adays

0.83

 kidding

0.80

entimes

0.77

 surprisingly

0.75

 Thoughts

0.75

Activations Density 1.210%

terms related to economic and political discussions

No Comments

No Known Activations