INDEX

Explanations

phrases related to technological concepts or coding structures

oai_token-act-pair · gpt-3.5-turbo

negations or phrases that express a lack of a particular quality or characteristic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 scatter

-0.71

 spiral

-0.67

vom

-0.63

 multiplier

-0.61

jog

-0.60

glers

-0.60

 relocation

-0.60

çīĪ

-0.59

 dispers

-0.59

 scattering

-0.59

POSITIVE LOGITS

yet

0.94

£

0.86

¹

0.85

½

0.84

_>

0.80

eas

0.80

cedented

0.78

°

0.78

Ĭ

0.78

atures

0.78

Activations Density 0.202%

phrases related to technological concepts or coding structures

negations or phrases that express a lack of a particular quality or characteristic

No Comments

No Known Activations