INDEX

Explanations

words ending in 'h' with a high activation value

oai_token-act-pair · gpt-3.5-turbo

instances of the symbol 'h'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ãĤ´ãĥ³

-0.91

ãĥ¯

-0.89

éĹĺ

-0.87

ãĥ¼ãĥĨãĤ£

-0.74

ortium

-0.74

ãĥ´ãĤ¡

-0.73

DragonMagazine

-0.73

EStream

-0.69

ierrez

-0.67

ãĥ¼ãĤ¯

-0.67

POSITIVE LOGITS

oused

1.27

ousing

1.17

awk

1.14

ulk

1.12

acking

1.12

anging

1.09

idd

1.08

annah

1.06

olly

1.05

oney

1.05

Activations Density 0.018%

words ending in 'h' with a high activation value

instances of the symbol 'h'

No Comments

No Known Activations