INDEX

Explanations

phrases related to specific locations or destinations

oai_token-act-pair · gpt-3.5-turbo

the article "a" in different contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Actions

-0.73

grounds

-0.70

 indexes

-0.70

ATURES

-0.69

evidence

-0.69

Examples

-0.68

onduct

-0.68

Orig

-0.68

 Organizations

-0.67

mods

-0.66

POSITIVE LOGITS

 girlfriend

1.25

 boyfriend

1.16

 friend

1.15

 stint

1.12

job

1.10

 lifetime

1.10

 childhood

1.10

 haircut

1.08

 therapist

1.07

 lifelong

1.06

Activations Density 0.316%

phrases related to specific locations or destinations

the article "a" in different contexts

No Comments

No Known Activations