INDEX

Explanations

words associated with endings or conclusions

oai_token-act-pair · gpt-3.5-turbo

closing punctuation marks, indicating the end of sentences or segments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ategory

-0.76

ppo

-0.73

IGHTS

-0.72

kaya

-0.67

kefeller

-0.66

 absor

-0.65

alcohol

-0.65

PDATE

-0.64

 underest

-0.64

terness

-0.62

POSITIVE LOGITS

angered

1.02

orph

1.01

angering

0.95

ragon

0.94

lich

0.94

urance

0.93

erer

0.92

ering

0.88

ocrin

0.86

ulum

0.85

Activations Density 0.031%

words associated with endings or conclusions

closing punctuation marks, indicating the end of sentences or segments

No Comments

No Known Activations