INDEX

Explanations

words related to geographic locations and names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "gy"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

umer

-0.73

 Archdemon

-0.73

umers

-0.72

wcs

-0.70

ovo

-0.69

itures

-0.68

arium

-0.68

umerable

-0.68

ipeg

-0.65

itudinal

-0.63

POSITIVE LOGITS

gie

0.97

rics

0.85

cock

0.84

gian

0.81

psy

0.81

glers

0.80

roxy

0.77

busters

0.77

wig

0.75

gy

0.74

Activations Density 0.020%

words related to geographic locations and names

occurrences of the substring "gy"

No Comments

No Known Activations