INDEX

Explanations

locations involving mountains

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

Counter

-0.74

Student

-0.73

Factor

-0.70

sych

-0.70

Gender

-0.68

Sales

-0.67

eon

-0.67

Product

-0.65

Interview

-0.65

 Person

-0.64

POSITIVE LOGITS

 valley

1.22

 canyon

1.17

 vegetation

1.17

 valleys

1.15

 wetlands

1.12

 basin

1.11

 lake

1.11

 inhabited

1.10

 habitat

1.10

 ridge

1.08

Activations Density 1.752%

locations involving mountains

No Comments

No Known Activations