INDEX

Explanations

adjectives indicating a large degree, such as immense, tremendous, and enormous

oai_token-act-pair · gpt-3.5-turbo

words expressing large magnitude or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

crow

-0.92

okes

-0.84

tag

-0.82

icle

-0.80

cling

-0.79

arers

-0.78

©¶æ

-0.77

ney

-0.76

ja

-0.75

olog

-0.75

POSITIVE LOGITS

 amounts

1.08

 amount

0.96

 quantities

0.94

 wealth

0.85

 strides

0.85

 importance

0.84

 hardship

0.84

 volumes

0.80

 accomplishment

0.79

 gratitude

0.78

Activations Density 0.046%

adjectives indicating a large degree, such as immense, tremendous, and enormous

words expressing large magnitude or significance

No Comments

No Known Activations