INDEX

Explanations

proper names or phrases related to people or characters with a specific name 'Dario'

oai_token-act-pair · gpt-3.5-turbo

references to characters or roles in film or television

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

ivities

-1.10

urations

-0.87

urers

-0.85

uring

-0.85

ues

-0.82

endor

-0.81

uration

-0.80

iple

-0.80

erton

-0.80

iency

-0.79

POSITIVE LOGITS

BuyableInstoreAndOnline

0.78

 Typhoon

0.74

BILITY

0.74

cia

0.73

 Bots

0.71

cles

0.71

xual

0.70

vernment

0.70

active

0.69

nces

0.68

Activations Density 0.031%

proper names or phrases related to people or characters with a specific name 'Dario'

references to characters or roles in film or television

No Comments

No Known Activations