INDEX

Explanations

words related to observations and findings in various studies, cases, or situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "a"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Edit

-0.80

Contents

-0.75

 Jagu

-0.71

 Estimates

-0.70

anism

-0.70

 knows

-0.69

achu

-0.69

ographs

-0.68

ESPN

-0.67

tests

-0.67

POSITIVE LOGITS

lot

1.21

 plethora

1.07

 glimpse

1.05

 multitude

1.03

 significant

1.02

few

1.01

 flurry

1.00

 bunch

1.00

 tremendous

0.99

 dramatic

0.97

Activations Density 0.302%

words related to observations and findings in various studies, cases, or situations

instances of the word "a"

No Comments

No Known Activations