INDEX

Explanations

instances of the word "Another" followed by various contexts or scenarios

oai_token-act-pair · gpt-3.5-turbo

repetitive phrases starting with the word "Another."

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

hips

-0.74

ivas

-0.73

alties

-0.71

ãĤ¬

-0.70

obar

-0.65

present

-0.65

icides

-0.64

riages

-0.62

 otherwise

-0.61

ouls

-0.61

POSITIVE LOGITS

worldly

0.99

 notch

0.81

 unnamed

0.80

 example

0.75

 notable

0.75

 drawback

0.74

wcs

0.72

 pecul

0.71

 casualty

0.71

 reason

0.70

Activations Density 0.035%

instances of the word "Another" followed by various contexts or scenarios

repetitive phrases starting with the word "Another."

No Comments

No Known Activations