INDEX

Explanations

phrases related to significant changes or shifts

oai_token-act-pair · gpt-3.5-turbo

phrases about changes in conditions or parameters

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

YES

-0.73

soever

-0.69

¤

-0.67

Ĭ

-0.67

 hanged

-0.66

DEV

-0.66

netflix

-0.66

rs

-0.65

ague

-0.65

linger

-0.65

POSITIVE LOGITS

efficiency

1.04

 regards

1.00

effic

0.99

 relation

0.97

 favor

0.93

 accordance

0.92

 lieu

0.91

animate

0.89

 conjunction

0.87

 order

0.85

Activations Density 0.099%

phrases related to significant changes or shifts

phrases about changes in conditions or parameters

No Comments

No Known Activations