INDEX

Explanations

references to cars

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

 Flavoring

-0.87

 Seym

-0.82

xual

-0.76

scl

-0.75

 Lans

-0.74

naires

-0.73

edIn

-0.70

é¾įå¥ĳå£«

-0.68

ãģį

-0.67

enance

-0.67

POSITIVE LOGITS

ousel

1.55

penter

1.42

riages

1.41

riage

1.17

rera

1.11

olina

1.05

negie

1.04

wash

1.02

riers

1.00

 dealership

0.98

Activations Density 0.029%

references to cars

No Comments

No Known Activations