INDEX

Explanations

names containing the substring "ve"

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names

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

¥µ

-0.67

illance

-0.67

igators

-0.67

direction

-0.67

upuncture

-0.65

izoph

-0.65

href

-0.64

stanbul

-0.62

igator

-0.61

dict

-0.61

POSITIVE LOGITS

 Robinson

1.05

 McKay

1.00

 Michaels

0.99

 Richards

0.98

 Coleman

0.98

 Farrell

0.98

 Ryder

0.97

 Peters

0.96

 McCull

0.95

 Cumm

0.94

Activations Density 0.215%

names containing the substring "ve"

proper nouns or names

No Comments

No Known Activations