INDEX

Explanations

phrases related to events or actions happening inside a specific location

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" used repeatedly across various contexts

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

ļ

-0.75

illac

-0.70

pent

-0.69

KEY

-0.69

picture

-0.68

orks

-0.64

uploads

-0.64

CAST

-0.63

wordpress

-0.61

rest

-0.61

POSITIVE LOGITS

clud

0.88

strument

0.77

clusive

0.75

vention

0.74

 thereto

0.73

cluded

0.73

flation

0.68

ners

0.65

clusion

0.64

backer

0.63

Activations Density 0.047%

phrases related to events or actions happening inside a specific location

the preposition "in" used repeatedly across various contexts

No Comments

No Known Activations