INDEX

Explanations

references to specific entities or names

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

Ø©

-0.69

 Malf

-0.69

 Murdoch

-0.63

IBLE

-0.61

 celebr

-0.61

 systematic

-0.60

ÙĴ

-0.60

phrine

-0.60

 expires

-0.59

 Collider

-0.59

POSITIVE LOGITS

ratom

1.16

orea

1.16

ernels

1.06

won

1.06

etchup

1.05

lar

1.05

rieg

1.05

laus

1.04

ernel

1.01

ansas

1.01

Activations Density 1.842%

references to specific entities or names

No Comments

No Known Activations