INDEX

Explanations

words related to personal preferences

oai_token-act-pair · gpt-3.5-turbo

references to personal preferences and choices

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

bane

-0.79

mans

-0.76

wordpress

-0.75

mberg

-0.74

kj

-0.73

Interstitial

-0.72

icles

-0.72

xx

-0.70

ãĤ¤ãĥĪ

-0.70

angel

-0.68

POSITIVE LOGITS

 preferences

1.00

 favoring

0.94

 preference

0.87

eering

0.84

yip

0.84

 pane

0.80

ļéĨĴ

0.79

 elig

0.79

 favoured

0.78

 selection

0.73

Activations Density 0.019%

words related to personal preferences

references to personal preferences and choices

No Comments

No Known Activations