INDEX

Explanations

mentions of the English language

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "English" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enges

-0.79

psy

-0.78

uder

-0.75

atl

-0.73

ĸļ

-0.73

Ara

-0.72

stals

-0.71

cients

-0.71

Downloadha

-0.70

ertodd

-0.70

POSITIVE LOGITS

 translation

1.06

 translations

1.00

language

0.98

speaking

0.96

 muff

0.96

 subtitles

0.96

shire

0.91

man

0.90

 Language

0.90

 language

0.88

Activations Density 0.024%

mentions of the English language

occurrences of the word "English" in various contexts

No Comments

No Known Activations