INDEX

Explanations

definitions or explanations of words

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

DERR

-0.78

jri

-0.76

ierrez

-0.70

oÄŁ

-0.70

ithing

-0.68

ramid

-0.68

 Skydragon

-0.68

psey

-0.68

isner

-0.66

cffff

-0.64

POSITIVE LOGITS

mith

1.15

sworth

1.05

 uttered

0.89

ology

0.87

 coined

0.86

icide

0.84

ifier

0.84

mark

0.82

witz

0.80

cloud

0.80

Activations Density 0.619%

definitions or explanations of words

No Comments

No Known Activations