INDEX

Explanations

proper nouns and particular names or terms

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ£

-0.78

ts

-0.72

tin

-0.68

judicial

-0.66

few

-0.64

Äĩ

-0.61

bably

-0.60

scope

-0.60

 lion

-0.59

ASED

-0.59

POSITIVE LOGITS

alid

1.17

ystem

1.14

ession

1.11

ometimes

1.07

alon

1.07

essions

1.06

ymph

1.05

ippi

1.04

achusetts

1.02

assin

1.02

Activations Density 0.016%

proper nouns and particular names or terms

No Comments

No Known Activations