INDEX

Explanations

mentions of the word "rose" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the word "rose" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

egu

-0.69

essee

-0.68

oha

-0.60

eren

-0.60

eties

-0.60

ociation

-0.60

 nature

-0.60

_____

-0.59

eport

-0.59

omal

-0.57

POSITIVE LOGITS

mary

1.09

xual

1.08

rose

0.92

frog

0.88

 bushes

0.87

undown

0.77

borough

0.70

ceed

0.70

ulic

0.70

Cum

0.70

Activations Density 0.013%

mentions of the word "rose" in various contexts

references to the word "rose" in various contexts

No Comments

No Known Activations