INDEX

Explanations

words related to legal cases or people involved in legal disputes

oai_token-act-pair · gpt-3.5-turbo

mentions of specific medical cases or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ergy

-0.75

ager

-0.71

alogue

-0.70

 WATCHED

-0.70

NESS

-0.69

iple

-0.67

box

-0.64

ivity

-0.64

alore

-0.62

arians

-0.62

POSITIVE LOGITS

ppe

1.36

zza

1.34

BILITY

1.10

ppa

1.08

pered

0.99

ffe

0.97

zzo

0.95

BILITIES

0.92

ea

0.91

ÅĤ

0.91

Activations Density 0.093%

words related to legal cases or people involved in legal disputes

mentions of specific medical cases or conditions

No Comments

No Known Activations