INDEX

Explanations

phrases related to providing recommendations or advice

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

'.

-0.72

 ........

-0.70

 ..............

-0.70

".

-0.66

 ................

-0.63

liv

-0.62

."

-0.62

 ..........

-0.61

.........

-0.57

·

-0.57

POSITIVE LOGITS

 involves

0.69

 occurs

0.67

ever

0.66

 relates

0.64

 success

0.64

 bothers

0.63

 varies

0.62

 improvement

0.62

 interested

0.59

 ever

0.59

Activations Density 0.324%

phrases related to providing recommendations or advice

No Comments

No Known Activations