INDEX

Explanations

keywords related to the brand "Toy" with varying levels of specificity

oai_token-act-pair · gpt-3.5-turbo

references to the "Toy" brand and associated media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

etheless

-0.77

 livest

-0.75

 confir

-0.72

icter

-0.70

 Hurricanes

-0.68

andestine

-0.65

 drained

-0.65

aunder

-0.64

sembly

-0.64

 lett

-0.64

POSITIVE LOGITS

ota

0.95

Toy

0.94

oga

0.89

shop

0.84

Toy

0.83

owa

0.81

hammer

0.81

ograp

0.80

omi

0.80

oho

0.79

Activations Density 0.010%

keywords related to the brand "Toy" with varying levels of specificity

references to the "Toy" brand and associated media

No Comments

No Known Activations