INDEX

Explanations

proper nouns relating to famous people or specific scenarios

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

pim

-0.60

REDACTED

-0.59

 notch

-0.55

 Metatron

-0.54

 reconc

-0.54

ACTED

-0.53

 tumble

-0.53

Spoiler

-0.52

 clown

-0.52

WB

-0.52

POSITIVE LOGITS

enei

0.80

ilian

0.78

chel

0.77

eli

0.77

ili

0.76

abyte

0.76

eto

0.76

esh

0.75

emon

0.74

iber

0.74

Activations Density 0.908%

proper nouns relating to famous people or specific scenarios

No Comments

No Known Activations