INDEX

Explanations

instances of action words

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "to do" indicating actions or tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

lights

-0.80

mare

-0.71

ussen

-0.67

pa

-0.65

wagen

-0.64

Reviewer

-0.62

tight

-0.62

 Handling

-0.62

ware

-0.61

bane

-0.59

POSITIVE LOGITS

omsday

0.99

pez

0.98

omething

0.91

ppel

0.85

lez

0.78

ggy

0.78

oms

0.77

ozy

0.77

lyak

0.76

 something

0.75

Activations Density 0.102%

instances of action words

instances of the phrase "to do" indicating actions or tasks

No Comments

No Known Activations