INDEX

Explanations

names of organizations or teams

oai_token-act-pair · gpt-3.5-turbo

plural noun forms related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

PDATE

-0.91

âĸ¬

-0.85

Loop

-0.71

Chart

-0.67

 Azerb

-0.66

 practition

-0.66

Vari

-0.65

ERROR

-0.64

CHAR

-0.63

 disability

-0.63

POSITIVE LOGITS

aurus

1.28

hip

1.22

ervatives

1.15

hips

1.10

ilver

1.03

ervative

1.01

paces

1.00

poons

0.99

cale

0.99

ucker

0.97

Activations Density 0.224%

names of organizations or teams

plural noun forms related to various subjects

No Comments

No Known Activations