INDEX

Explanations

names or words containing "te"

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the token "te" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 sweep

-0.70

ipolar

-0.67

usher

-0.62

owsky

-0.62

alos

-0.62

 footing

-0.61

interrupted

-0.61

antha

-0.61

lessly

-0.60

çĶŁ

-0.56

POSITIVE LOGITS

brate

1.58

brates

1.56

levision

1.29

ller

1.27

llers

1.23

achers

1.18

legraph

1.11

achable

1.09

legram

1.09

aching

1.08

Activations Density 0.039%

names or words containing "te"

the occurrence of the token "te" in various contexts

No Comments

No Known Activations