INDEX

Explanations

statements indicating approval or positive evaluation of various ideas or situations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

eds

-0.88

doms

-0.87

lees

-0.80

ancies

-0.79

stals

-0.78

events

-0.78

gemony

-0.76

RAW

-0.76

onduct

-0.74

isms

-0.74

POSITIVE LOGITS

 idea

1.19

 example

1.18

 indicator

1.16

 asset

1.15

 reminder

1.15

 thing

1.14

 indication

1.14

 opportunity

1.11

 predictor

1.10

 approximation

1.10

Activations Density 0.081%

statements indicating approval or positive evaluation of various ideas or situations

No Comments

No Known Activations