INDEX

Explanations

names of individuals or locations

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

ivity

-0.98

istics

-0.87

ually

-0.83

iants

-0.83

iveness

-0.81

istically

-0.81

inant

-0.78

iant

-0.78

opher

-0.77

oted

-0.76

POSITIVE LOGITS

lic

0.92

cles

0.82

ursed

0.80

lys

0.73

odies

0.72

rito

0.70

mble

0.67

rette

0.67

anners

0.66

ONSORED

0.66

Activations Density 0.076%

names of individuals or locations

No Comments

No Known Activations