INDEX

Explanations

mentions of the name "Michele" and similar proper nouns

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

hip

-0.78

hips

-0.78

holes

-0.77

erker

-0.75

emouth

-0.72

\\\\\\\\

-0.71

ĸļ

-0.71

olver

-0.70

ibaba

-0.69

raint

-0.69

POSITIVE LOGITS

 Bach

1.23

 Michele

1.00

 Pelosi

0.94

 Tome

0.84

Fey

0.83

 Schmidt

0.79

kson

0.79

 Crist

0.77

tti

0.77

tta

0.77

Activations Density 0.004%

mentions of the name "Michele" and similar proper nouns

No Comments

No Known Activations