INDEX

Explanations

capital letters in the middle of a sentence signaling a name or title

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'B'

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

 Gutenberg

-0.73

 dere

-0.67

wcsstore

-0.66

 choke

-0.64

 impunity

-0.63

 glow

-0.63

 inflic

-0.61

 Pharaoh

-0.60

por

-0.60

rpm

-0.60

POSITIVE LOGITS

rief

1.16

odies

1.15

ETA

1.11

anned

1.08

ranch

1.07

rows

1.06

OTH

1.05

urt

1.05

achel

1.02

rug

1.02

Activations Density 0.046%

capital letters in the middle of a sentence signaling a name or title

instances of the letter 'B'

No Comments

No Known Activations