INDEX

Explanations

mentions related to the country "New Zealand"

oai_token-act-pair · gpt-3.5-turbo

mentions of locations and geographical references

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

estation

-0.75

vest

-0.74

lat

-0.73

adic

-0.72

blers

-0.72

matically

-0.71

accessible

-0.69

veyard

-0.69

hift

-0.69

 Graveyard

-0.69

POSITIVE LOGITS

xon

0.69

ĪĴ

0.66

æĪ¦

0.65

tones

0.64

 Waters

0.64

 Franch

0.63

theless

0.63

 Mellon

0.62

mone

0.61

 VIDEOS

0.61

Activations Density 0.055%

mentions related to the country "New Zealand"

mentions of locations and geographical references

No Comments

No Known Activations