INDEX

Explanations

phrases indicating strong beliefs or predictions

oai_token-act-pair · gpt-3.5-turbo

modal verbs indicating possibility and capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

CTR

-0.65

 Arcade

-0.64

 Steps

-0.63

 Indie

-0.62

 Goods

-0.61

 Provided

-0.60

 palms

-0.60

BG

-0.58

 mats

-0.58

olor

-0.57

POSITIVE LOGITS

lement

0.94

urious

0.83

nt

0.82

mint

0.79

ered

0.78

't

0.78

elt

0.76

anism

0.75

nir

0.75

scl

0.74

Activations Density 0.145%

phrases indicating strong beliefs or predictions

modal verbs indicating possibility and capability

No Comments

No Known Activations