INDEX

Explanations

descriptive phrases or opinions

oai_token-act-pair · gpt-3.5-turbo

references to significant events or milestones

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

soDeliveryDate

-0.69

arine

-0.69

WT

-0.68

igate

-0.66

WP

-0.64

alde

-0.63

$$$$

-0.61

ä»£

-0.60

unks

-0.60

agos

-0.60

POSITIVE LOGITS

 nonetheless

1.47

 nevertheless

1.26

etheless

1.03

 still

0.80

 strangely

0.76

 awfully

0.68

 unmist

0.67

 adamant

0.67

 overshadowed

0.67

 acknowled

0.66

Activations Density 1.172%

descriptive phrases or opinions

references to significant events or milestones

No Comments

No Known Activations