INDEX

Explanations

adjectives or phrases indicating a judgment or evaluation

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

YR

-0.72

VEL

-0.70

MED

-0.66

umsy

-0.66

alk

-0.65

arning

-0.64

por

-0.63

oval

-0.62

NYSE

-0.62

culation

-0.61

POSITIVE LOGITS

 impressions

0.82

 tastes

0.79

 qualifies

0.76

 constitutes

0.75

 interests

0.74

 responsibilities

0.71

ilege

0.68

 qualities

0.67

iates

0.67

 habits

0.66

Activations Density 0.032%

adjectives or phrases indicating a judgment or evaluation

No Comments

No Known Activations