INDEX

Explanations

the letter 'T' followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to the letter "T"

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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.84

theless

-0.80

 destro

-0.74

 ment

-0.72

EStream

-0.70

 cannabin

-0.67

 actionGroup

-0.66

espie

-0.63

 Senegal

-0.63

wagen

-0.62

POSITIVE LOGITS

ribute

1.29

ARGET

1.27

olerance

1.22

ributes

1.18

uple

1.17

ractor

1.16

empt

1.13

ucked

1.13

asks

1.12

agged

1.11

Activations Density 0.049%

the letter 'T' followed by a number

references to the letter "T"

No Comments

No Known Activations