INDEX

Explanations

references to shops or stores

oai_token-act-pair · gpt-3.5-turbo

mentions of retail establishments or shops

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

ioxide

-0.69

 dreaded

-0.67

 Marketable

-0.65

theless

-0.63

 IPCC

-0.63

Mub

-0.61

 Sheen

-0.61

âĢ¢âĢ¢âĢ¢âĢ¢

-0.61

thia

-0.60

 flakes

-0.59

POSITIVE LOGITS

keeper

1.31

keepers

1.30

lifting

1.14

shop

1.11

worn

1.00

kie

0.98

room

0.96

folk

0.95

 shop

0.93

keep

0.92

Activations Density 0.014%

references to shops or stores

mentions of retail establishments or shops

No Comments

No Known Activations