INDEX

Explanations

instances of the word "before" followed by an action

oai_token-act-pair · gpt-3.5-turbo

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

geist

-0.78

WIND

-0.75

hack

-0.71

ISM

-0.71

Force

-0.70

framework

-0.69

aez

-0.69

rone

-0.69

luaj

-0.68

CAP

-0.67

POSITIVE LOGITS

 settling

1.20

 disappearing

1.20

 returning

1.17

 realizing

1.14

 concluding

1.13

 reaching

1.11

 deciding

1.10

 fading

1.09

 finally

1.08

 retreating

1.07

Activations Density 0.067%

instances of the word "before" followed by an action

No Comments

No Known Activations