INDEX

Explanations

advertisements within the text

oai_token-act-pair · gpt-3.5-turbo

occurrences of advertisements within the text

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

stra

-0.66

ties

-0.64

 wound

-0.63

 retri

-0.62

©¶æ

-0.61

graded

-0.61

 perspect

-0.60

 contingent

-0.57

balls

-0.57

Gaw

-0.56

POSITIVE LOGITS

 Advertisement

1.15

 Continue

1.04

ieu

0.82

Skip

0.78

advertising

0.77

usercontent

0.75

@@

0.74

Continue

0.74

Images

0.73

Image

0.70

Activations Density 0.021%

advertisements within the text

occurrences of advertisements within the text

No Comments

No Known Activations