INDEX

Explanations

comparative descriptions related to the level or quantity of something, especially when it is relatively high

oai_token-act-pair · gpt-3.5-turbo

phrases expressing high levels or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ond

-0.72

sov

-0.71

Rect

-0.70

Ã¨

-0.69

Â¯Â¯

-0.68

adier

-0.67

Maker

-0.67

herer

-0.67

pty

-0.66

arian

-0.66

POSITIVE LOGITS

(>

1.01

 proportion

1.00

 amounts

0.99

 enough

0.99

 paced

0.98

 levels

0.97

 percentage

0.96

 concentrations

0.93

 probability

0.93

 degree

0.92

Activations Density 0.081%

comparative descriptions related to the level or quantity of something, especially when it is relatively high

phrases expressing high levels or quantities

No Comments

No Known Activations