INDEX

Explanations

instances where someone is considering or attempting something

oai_token-act-pair · gpt-3.5-turbo

phrases expressing the intention or suggestion to attempt something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

head

-0.70

dylib

-0.70

atform

-0.68

hip

-0.67

Plot

-0.66

lav

-0.65

thus

-0.64

cedented

-0.62

edly

-0.62

\-

-0.60

POSITIVE LOGITS

 unsuccessfully

0.97

nir

0.89

 harder

0.77

enged

0.68

ichick

0.67

onies

0.65

 desperately

0.65

ipers

0.63

anke

0.63

ggle

0.63

Activations Density 0.052%

instances where someone is considering or attempting something

phrases expressing the intention or suggestion to attempt something

No Comments

No Known Activations