INDEX

Explanations

references to the word "ms" at different activation levels

oai_token-act-pair · gpt-3.5-turbo

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

redo

-0.70

 Rican

-0.69

OPLE

-0.66

 Rico

-0.64

 Zoro

-0.63

 Strauss

-0.63

 acids

-0.62

 acid

-0.60

ASED

-0.60

Ram

-0.59

POSITIVE LOGITS

pace

1.06

achus

1.04

erver

1.03

giving

0.98

mble

0.95

manship

0.94

creen

0.92

fw

0.92

ophon

0.90

cript

0.89

Activations Density 0.020%

references to the word "ms" at different activation levels

No Comments

No Known Activations