INDEX

Explanations

terms related to meat, food production, and culinary 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_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

unci

-0.78

orsche

-0.76

agall

-0.66

 Learned

-0.66

antis

-0.65

 Stanton

-0.64

ipolar

-0.64

ordinate

-0.64

 Telecommunications

-0.63

owered

-0.63

POSITIVE LOGITS

balls

1.15

meat

1.14

cake

1.10

 slic

1.05

bowl

1.05

skin

1.03

 broth

1.01

lo

1.00

heads

0.99

food

0.97

Activations Density 0.274%

terms related to meat, food production, and culinary activities

No Comments

No Known Activations