INDEX

Explanations

words related to caring or concern

oai_token-act-pair · gpt-3.5-turbo

expressions of concern or indifference

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

ãĥĥãĥī

-0.73

oute

-0.73

è¦ļéĨĴ

-0.68

ãĥ³ãĤ¸

-0.67

GV

-0.65

UES

-0.65

jam

-0.65

 sclerosis

-0.62

 resume

-0.61

adr

-0.61

POSITIVE LOGITS

lessly

1.15

taker

1.15

 passionately

1.03

 cared

0.99

fully

0.90

giving

0.86

bear

0.81

tta

0.80

lessness

0.79

der

0.79

Activations Density 0.015%

words related to caring or concern

expressions of concern or indifference

No Comments

No Known Activations