INDEX

Explanations

numerical values indicating weight in pounds

oai_token-act-pair · gpt-3.5-turbo

references to weight measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ende

-0.70

hist

-0.66

 guiActiveUnfocused

-0.66

 segregation

-0.61

lege

-0.60

venge

-0.60

este

-0.59

haps

-0.59

 reconstruction

-0.58

ment

-0.58

POSITIVE LOGITS

 pounds

3.79

lbs

2.62

lbs

2.51

 pound

2.44

pound

2.32

 kilograms

2.01

lb

1.84

 ounces

1.82

lb

1.69

 Pound

1.66

Activations Density 0.013%

numerical values indicating weight in pounds

references to weight measurements

No Comments

No Known Activations