INDEX

Explanations

capitalized 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

ifice

-0.77

asta

-0.76

ugu

-0.74

 Caption

-0.72

amaru

-0.72

ICLE

-0.68

lus

-0.68

annel

-0.68

lov

-0.67

ashtra

-0.66

POSITIVE LOGITS

 thirds

1.60

 halves

1.21

 dozen

1.19

 hundred

1.09

 weeks

1.09

fold

1.08

teenth

1.01

 separate

0.94

nd

0.94

 sets

0.92

Activations Density 0.401%

capitalized words

No Comments

No Known Activations