INDEX

Explanations

references to specific terms and concepts

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

Lov

-0.64

pload

-0.61

Fall

-0.60

 paternity

-0.60

 Bren

-0.59

 mango

-0.58

inn

-0.58

Ner

-0.57

 Fairfax

-0.56

POSITIVE LOGITS

 thereof

0.92

quickShipAvailable

0.90

 alike

0.89

abouts

0.89

.}

0.80

hots

0.78

.>>

0.77

.?

0.77

.,

0.76

.:

0.76

Activations Density 0.081%

references to specific terms and concepts

No Comments

No Known Activations