INDEX

Explanations

past tense verbs indicating completed actions

oai_token-act-pair · gpt-3.5-turbo

actions or experiences related to work and service

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

nr

-0.64

VPN

-0.63

Accessory

-0.63

itter

-0.63

Pierre

-0.62

Australia

-0.61

ingers

-0.61

Zone

-0.61

States

-0.61

Dre

-0.60

POSITIVE LOGITS

ĸļ

0.89

 hitherto

0.87

 since

0.80

 lately

0.79

 previously

0.76

 sufficiently

0.75

gone

0.70

 proven

0.68

 countless

0.67

ufact

0.65

Activations Density 0.388%

past tense verbs indicating completed actions

actions or experiences related to work and service

No Comments

No Known Activations