INDEX

Explanations

locations or entities with 'In'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "In" or similar prepositions indicating location or context

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

 afar

-0.69

etheless

-0.68

toggle

-0.66

 lett

-0.65

OPLE

-0.64

 needles

-0.63

terday

-0.63

 flick

-0.59

 downhill

-0.59

erous

-0.57

POSITIVE LOGITS

itialized

0.94

vent

0.94

omal

0.87

vern

0.86

och

0.85

acon

0.84

vis

0.83

sel

0.83

omer

0.81

grid

0.80

Activations Density 0.141%

locations or entities with 'In'

occurrences of the word "In" or similar prepositions indicating location or context

No Comments

No Known Activations