INDEX

Explanations

locations or settings described with detailed attributes

oai_token-act-pair · gpt-3.5-turbo

quantitative descriptors and the use of the article "a."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

votes

-0.88

issues

-0.87

Americans

-0.80

 answers

-0.78

effects

-0.77

apps

-0.76

oons

-0.75

attacks

-0.73

facts

-0.73

 Issues

-0.73

POSITIVE LOGITS

 mixture

1.08

 combination

1.02

 series

1.02

 variety

1.01

 handful

0.99

 rudimentary

0.99

 succession

0.98

 sizeable

0.98

 triangular

0.97

 small

0.97

Activations Density 0.469%

locations or settings described with detailed attributes

quantitative descriptors and the use of the article "a."

No Comments

No Known Activations