INDEX

Explanations

names or words containing the syllable "y."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'y'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

DERR

-0.71

 delinqu

-0.68

Au

-0.61

 prov

-0.58

INESS

-0.57

 Equip

-0.56

 Presidency

-0.56

 coord

-0.55

 idle

-0.55

]-

-0.54

POSITIVE LOGITS

vind

1.02

enne

1.02

ramid

0.99

vette

0.93

nton

0.92

ongyang

0.91

chell

0.91

orkshire

0.89

ielding

0.89

nda

0.89

Activations Density 0.048%

names or words containing the syllable "y."

occurrences of the letter 'y'

No Comments

No Known Activations