INDEX

Explanations

phrases regarding quantities or statistics

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

-0.81

heet

-0.79

ãĥķãĤ©

-0.72

UAL

-0.70

PDF

-0.69

wcs

-0.69

henko

-0.69

merga

-0.69

utan

-0.68

agascar

-0.68

POSITIVE LOGITS

 apartment

0.93

 courthouse

0.91

 apartments

0.89

 Parliament

0.85

 parliament

0.83

 Hogwarts

0.83

 dorm

0.83

 hotel

0.82

 Stamford

0.81

 hotels

0.81

Activations Density 0.068%

phrases regarding quantities or statistics

No Comments

No Known Activations