INDEX

Explanations

Latin characters and punctuation

oai_token-act-pair · gpt-3.5-turbo

symbols or characters that are not standard text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

bris

-0.89

vern

-0.89

vantage

-0.88

agen

-0.82

vier

-0.81

imore

-0.81

osion

-0.81

ussian

-0.80

ction

-0.80

apers

-0.79

POSITIVE LOGITS

 namely

0.93

 Which

0.82

 whereas

0.81

 yeah

0.78

 implying

0.75

 Granted

0.74

 secondly

0.74

 culminating

0.73

 whence

0.72

 ********************************

0.72

Activations Density 0.178%

Latin characters and punctuation

symbols or characters that are not standard text

No Comments

No Known Activations