INDEX

Explanations

mentions of a specific location named Les

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the name "Les" or variations of it

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

ICE

-0.80

ACTED

-0.72

DERR

-0.71

ãĥ¼ãĥĨãĤ£

-0.71

YING

-0.68

ANI

-0.67

è¦ļéĨĴ

-0.66

ĻĤ

-0.66

ARK

-0.66

ãĥĥãĥĪ

-0.66

POSITIVE LOGITS

bians

1.13

bian

0.93

ukemia

0.81

bourg

0.81

nar

0.81

mut

0.80

leys

0.80

wana

0.78

agues

0.78

Les

0.78

Activations Density 0.012%

mentions of a specific location named Les

repeated mentions of the name "Les" or variations of it

No Comments

No Known Activations