INDEX

Explanations

mentions of a specific media outlet, "The Globe"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Globe" and related references to news organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ted

-0.87

enium

-0.83

ramid

-0.83

ball

-0.80

mented

-0.80

ivated

-0.79

meric

-0.78

sen

-0.77

terday

-0.75

hered

-0.75

POSITIVE LOGITS

 Rouge

0.74

 Scotia

0.73

 Globe

0.72

OSE

0.68

ose

0.65

vernment

0.64

zzle

0.64

 Manitoba

0.62

 Newspaper

0.62

Eth

0.61

Activations Density 0.047%

mentions of a specific media outlet, "The Globe"

mentions of the word "Globe" and related references to news organizations

No Comments

No Known Activations