INDEX

Explanations

names of countries and political figures

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

ONEY

-0.68

GMT

-0.61

 ende

-0.60

irlf

-0.59

pak

-0.58

SHARE

-0.57

pu

-0.57

CHECK

-0.56

KEY

-0.56

natureconservancy

-0.56

POSITIVE LOGITS

tenance

0.91

osterone

0.91

llor

0.78

roying

0.77

riors

0.75

 hybrids

0.71

vised

0.68

quartered

0.68

pared

0.66

acters

0.66

Activations Density 1.235%

names of countries and political figures

No Comments

No Known Activations