INDEX

Explanations

mentions of people's names

oai_token-act-pair · gpt-3.5-turbo

the letter "l" in various contexts

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

 tremend

-0.70

 constitu

-0.70

ãĥ¯ãĥ³

-0.69

ãĥ¼ãĥĨãĤ£

-0.67

ħĭ

-0.67

 stoked

-0.66

 hemor

-0.63

ItemTracker

-0.63

 confir

-0.62

 spirited

-0.61

POSITIVE LOGITS

ayers

1.22

ibraries

1.12

ateral

1.11

yrics

1.11

ifestyle

1.10

azy

1.08

ounge

1.07

opez

1.06

oyd

1.06

ava

1.02

Activations Density 0.035%

mentions of people's names

the letter "l" in various contexts

No Comments

No Known Activations