INDEX

Explanations

words ending in 'ense'

oai_token-act-pair · gpt-3.5-turbo

words related to sensory experiences or sensations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

skill

-0.62

OGR

-0.61

 apprentices

-0.61

 groom

-0.58

Accessory

-0.58

 ride

-0.58

 rough

-0.58

solete

-0.58

amous

-0.58

ODUCT

-0.57

POSITIVE LOGITS

mble

1.83

ense

1.33

iture

0.93

ENSE

0.91

enses

0.86

entimes

0.81

 Corpus

0.73

fw

0.73

yne

0.70

ly

0.70

Activations Density 0.014%

words ending in 'ense'

words related to sensory experiences or sensations

No Comments

No Known Activations