INDEX

Explanations

punctuation marks at the end of sentences

oai_token-act-pair · gpt-3.5-turbo

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

ļéĨĴ

-0.73

interstitial

-0.68

SHIP

-0.64

robe

-0.62

haul

-0.61

ername

-0.58

dragon

-0.58

olves

-0.55

ufact

-0.55

WAYS

-0.55

POSITIVE LOGITS

 however

1.27

 though

1.07

huh

1.04

 moreover

1.00

sir

0.96

 alas

0.95

 incidentally

0.88

eh

0.87

 anyway

0.87

 albeit

0.85

Activations Density 0.366%

punctuation marks at the end of sentences

No Comments

No Known Activations