INDEX

Explanations

names of specific locations such as stadiums, cities, and people

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

TING

-0.77

chell

-0.66

ters

-0.65

ATIONAL

-0.65

uated

-0.63

 Loaded

-0.63

OUT

-0.62

ATIONS

-0.62

Ö¼

-0.61

TE

-0.60

POSITIVE LOGITS

pin

1.30

pins

1.17

uin

1.16

doms

1.06

dom

1.00

DOM

0.95

killer

0.94

fish

0.92

 Kong

0.90

STON

0.88

Activations Density 0.224%

names of specific locations such as stadiums, cities, and people

No Comments

No Known Activations