INDEX

Explanations

terms related to geopolitical regions

oai_token-act-pair · gpt-3.5-turbo

references to a specific geographical region

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĥīãĥ©

-0.82

gement

-0.72

selage

-0.70

urations

-0.66

thood

-0.65

glers

-0.65

FIN

-0.64

veyard

-0.64

CRIPTION

-0.63

VID

-0.63

POSITIVE LOGITS

ally

0.83

 region

0.82

wide

0.78

region

0.76

 geographically

0.75

ional

0.74

wikipedia

0.70

side

0.70

 economically

0.70

area

0.70

Activations Density 0.015%

terms related to geopolitical regions

references to a specific geographical region

No Comments

No Known Activations