INDEX

Explanations

phrases related to actions or events involving harm or control by others

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "in the hands of."

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

 redes

-0.70

Ann

-0.69

andum

-0.67

nces

-0.64

 shaved

-0.64

icut

-0.63

 compr

-0.62

 hereby

-0.62

 Maple

-0.61

ollo

-0.61

POSITIVE LOGITS

lopp

0.75

FUL

0.69

mination

0.68

Gul

0.68

ulator

0.65

imately

0.64

adle

0.63

Storm

0.62

ible

0.59

innacle

0.59

Activations Density 0.053%

phrases related to actions or events involving harm or control by others

instances of the phrase "in the hands of."

No Comments

No Known Activations