INDEX

Explanations

phrases related to office furniture or items typically found on a desk

oai_token-act-pair · gpt-3.5-turbo

instances of the word "desk."

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

actionDate

-0.90

Interstitial

-0.88

 Adin

-0.83

Ô

-0.82

-0.72

 Adren

-0.68

ICO

-0.67

ICAN

-0.67

ESC

-0.66

ETH

-0.65

POSITIVE LOGITS

tops

1.78

 drawer

1.20

top

1.06

 Desk

1.00

 desk

0.97

chair

0.90

lift

0.86

pointer

0.85

Desk

0.80

 desks

0.80

Activations Density 0.017%

phrases related to office furniture or items typically found on a desk

instances of the word "desk."

No Comments

No Known Activations