INDEX

Explanations

words related to intense, risky, and life-threatening situations

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

iland

-0.73

wagen

-0.69

bial

-0.68

packs

-0.65

awaru

-0.65

 Saunders

-0.64

Fram

-0.62

ForgeModLoader

-0.61

Accessory

-0.61

hyde

-0.61

POSITIVE LOGITS

ention

1.03

itial

1.02

ensions

0.93

ellect

0.92

ract

0.92

itially

0.92

ellig

0.90

ension

0.89

ensive

0.88

icult

0.87

Activations Density 0.011%

words related to intense, risky, and life-threatening situations

No Comments

No Known Activations