INDEX

Explanations

words related to serving a purpose or function

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "serve" and its variations indicating function or purpose

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

razil

-0.82

ascus

-0.80

orne

-0.68

vu

-0.67

orph

-0.64

clone

-0.64

ilateral

-0.63

wcs

-0.62

orsi

-0.62

 Chase

-0.61

POSITIVE LOGITS

HTTP

0.81

 meals

0.80

 Serving

0.79

 SERV

0.78

maid

0.77

ctuary

0.76

 Serve

0.75

 serve

0.73

 kitchens

0.72

 horm

0.71

Activations Density 0.024%

words related to serving a purpose or function

instances of the verb "serve" and its variations indicating function or purpose

No Comments

No Known Activations