INDEX

Explanations

text related to people and their actions, interactions, and discussions

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

services

-0.64

earch

-0.64

veyard

-0.63

 Mandatory

-0.62

classic

-0.62

 Nationwide

-0.61

 Observatory

-0.61

 Oriental

-0.61

 Header

-0.61

 Millennium

-0.60

POSITIVE LOGITS

'd

1.49

'll

1.48

zbollah

1.31

resy

1.12

've

1.11

 knew

1.09

 swore

1.04

 didn

1.04

eded

1.04

 knows

1.03

Activations Density 0.722%

text related to people and their actions, interactions, and discussions

No Comments

No Known Activations