INDEX

Explanations

academic or scholarly terms and names

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

$.

-0.61

'.

-0.59

''.

-0.59

'.

-0.59

+.

-0.58

ãĢĤ

-0.57

".

-0.55

".

-0.55

%.

-0.54

.''.

-0.54

POSITIVE LOGITS

 Investigative

0.63

 Institute

0.62

 Research

0.61

nsic

0.61

 wrote

0.59

 researcher

0.59

 economist

0.58

 Forensic

0.58

 Press

0.58

 Arbit

0.57

Activations Density 0.999%

academic or scholarly terms and names

No Comments

No Known Activations