INDEX

Explanations

mentions of rates and fees

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 's'

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

 Leilan

-0.81

 hemor

-0.77

 thous

-0.75

ãĥ¼ãĥĨ

-0.74

 compar

-0.71

 behavi

-0.70

 subcontract

-0.64

 pree

-0.64

 destro

-0.62

 renal

-0.61

POSITIVE LOGITS

ouls

1.00

wered

0.99

anta

0.98

olo

0.95

arah

0.95

ayers

0.91

olution

0.91

acks

0.90

ources

0.89

essions

0.89

Activations Density 0.048%

mentions of rates and fees

occurrences of the letter 's'

No Comments

No Known Activations