INDEX

Explanations

terms related to caring, prioritizing, and considering value

oai_token-act-pair · gpt-3.5-turbo

phrases related to expressions of concern or care

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

UES

-0.73

GV

-0.67

jam

-0.65

è¦ļéĨĴ

-0.61

ãĥ³ãĤ¸

-0.61

anas

-0.60

ãĥĥãĥī

-0.59

 Rite

-0.59

CHA

-0.59

UE

-0.58

POSITIVE LOGITS

lessly

1.20

 passionately

1.10

taker

1.09

der

0.97

lessness

0.93

bear

0.88

fully

0.86

tta

0.82

giving

0.80

ened

0.79

Activations Density 0.023%

terms related to caring, prioritizing, and considering value

phrases related to expressions of concern or care

No Comments

No Known Activations