INDEX

Explanations

phrases related to social groups and activities

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

 Dame

-0.65

shire

-0.63

 Pradesh

-0.61

Bloomberg

-0.61

èª

-0.59

Rah

-0.59

 Latest

-0.59

 concess

-0.56

DAY

-0.56

ournal

-0.55

POSITIVE LOGITS

members

1.12

think

1.12

leader

1.09

 members

1.07

mates

1.04

ings

0.97

roups

0.97

 disbanded

0.96

ages

0.96

 member

0.91

Activations Density 0.549%

phrases related to social groups and activities

No Comments

No Known Activations