INDEX

Explanations

proper nouns related to places, names, and organizations

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

izoph

-0.70

ADRA

-0.66

Tokens

-0.62

Scotland

-0.60

 overwhelming

-0.60

Xi

-0.60

Compared

-0.59

 prohib

-0.58

 apex

-0.58

 unfavorable

-0.58

POSITIVE LOGITS

Jr

1.54

III

1.20

Sr

1.16

berger

1.11

baum

1.11

oglu

1.04

owski

1.03

iewicz

1.03

QC

1.03

ovich

1.03

Activations Density 1.032%

proper nouns related to places, names, and organizations

No Comments

No Known Activations