INDEX

Explanations

words related to geographical regions and cultural attributes

oai_token-act-pair · gpt-3.5-turbo

references to specific ethnic or cultural groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã©n

-0.63

 Anaheim

-0.59

AAA

-0.57

 Bernstein

-0.56

 blot

-0.55

ATT

-0.55

CCP

-0.55

 Kara

-0.55

haw

-0.54

QC

-0.54

POSITIVE LOGITS

 underscores

1.16

 illustrates

1.09

 suggests

1.05

 implies

1.03

 reinforces

1.02

 demonstrates

1.00

 seems

0.99

 depends

0.96

 indicates

0.96

 coincided

0.95

Activations Density 0.986%

words related to geographical regions and cultural attributes

references to specific ethnic or cultural groups

No Comments

No Known Activations