INDEX

Explanations

words related to visual perception and observation

oai_token-act-pair · gpt-3.5-turbo

references to vision or visual perception

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

ulative

-0.72

currency

-0.67

afort

-0.66

accompan

-0.65

emetery

-0.64

astically

-0.62

aceae

-0.60

orously

-0.59

itates

-0.58

idity

-0.58

POSITIVE LOGITS

seeing

1.90

lights

1.11

ings

1.10

mares

1.03

lines

0.98

 unseen

0.94

ening

0.92

glass

0.91

line

0.89

nings

0.87

Activations Density 0.045%

words related to visual perception and observation

references to vision or visual perception

No Comments

No Known Activations