INDEX

Explanations

instructional text related to settings and configurations

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

 skelet

-0.76

ingham

-0.69

 Hastings

-0.62

agos

-0.61

 Bung

-0.61

 TAMADRA

-0.60

 Constantin

-0.59

 digs

-0.58

 swept

-0.57

 immersed

-0.57

POSITIVE LOGITS

taboola

0.92

dayName

0.80

wcsstore

0.77

soever

0.76

hap

0.76

english

0.70

division

0.69

ecause

0.69

terness

0.68

CLASSIFIED

0.66

Activations Density 0.041%

instructional text related to settings and configurations

No Comments

No Known Activations