INDEX

Explanations

the word "all" appearing with high activation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "all."

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

aminer

-0.73

potion

-0.72

yip

-0.69

IDS

-0.64

lav

-0.64

zn

-0.64

ker

-0.63

assembly

-0.62

arter

-0.61

oute

-0.61

POSITIVE LOGITS

ocating

1.33

 kinds

1.17

igators

1.11

 sorts

1.10

igator

1.04

iances

1.02

owing

1.02

usions

1.00

ocated

0.94

ocate

0.93

Activations Density 0.139%

the word "all" appearing with high activation

occurrences of the word "all."

No Comments

No Known Activations