INDEX

Explanations

phrases starting with "What" followed by a statement or question

oai_token-act-pair · gpt-3.5-turbo

phrases that question or inquire about significant topics or matters

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

eering

-0.60

 circulation

-0.59

eer

-0.58

lich

-0.57

 receiving

-0.57

 stating

-0.56

gal

-0.56

interstitial

-0.55

 steril

-0.55

ifice

-0.54

POSITIVE LOGITS

soever

1.33

 happened

1.10

 happens

1.10

 distinguishes

0.99

 transpired

0.96

 else

0.92

 mattered

0.89

 happ

0.89

 bothers

0.85

 Happ

0.84

Activations Density 0.086%

phrases starting with "What" followed by a statement or question

phrases that question or inquire about significant topics or matters

No Comments

No Known Activations