INDEX

Explanations

proper nouns like names of people and organizations, especially related to politics or business

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rier

-0.75

holder

-0.69

ivities

-0.69

selves

-0.68

rap

-0.66

ishing

-0.66

atche

-0.66

ancies

-0.65

olk

-0.62

etheless

-0.62

POSITIVE LOGITS

ppo

1.17

ffic

0.99

ctl

0.97

cean

0.96

zzi

0.95

active

0.94

ÄŁ

0.93

hazard

0.91

zza

0.90

pec

0.88

Activations Density 0.033%

proper nouns like names of people and organizations, especially related to politics or business

No Comments

No Known Activations