INDEX

Explanations

words related to trustworthiness or credibility

oai_token-act-pair · gpt-3.5-turbo

instances of the substring "r"

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

eers

-0.83

 DRAG

-0.68

eer

-0.68

 Loft

-0.68

 Rising

-0.67

WAYS

-0.67

 Winds

-0.66

 staging

-0.64

 warr

-0.64

 dare

-0.64

POSITIVE LOGITS

inct

1.15

ilateral

1.01

angle

0.99

usted

0.98

angles

0.98

acy

0.98

acist

0.96

uder

0.96

angled

0.95

ushed

0.95

Activations Density 0.047%

words related to trustworthiness or credibility

instances of the substring "r"

No Comments

No Known Activations