INDEX

Explanations

numerical patterns in text, specifically 2-digit numbers and sequences of numbers

oai_token-act-pair · gpt-3.5-turbo

numerical values and age indicators

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

ãĤ©

-0.80

ashtra

-0.66

 cleaners

-0.65

ucci

-0.65

ãĥ£

-0.64

isance

-0.64

vana

-0.64

 fung

-0.63

iferation

-0.62

ãĥ¥

-0.59

POSITIVE LOGITS

deb

0.66

DVD

0.65

ousand

0.64

apore

0.64

 Samurai

0.62

WAY

0.62

Sok

0.60

eve

0.60

 poles

0.60

 Sail

0.60

Activations Density 0.221%

numerical patterns in text, specifically 2-digit numbers and sequences of numbers

numerical values and age indicators

No Comments

No Known Activations