INDEX

Explanations

instances of the word "had."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PI

-0.67

bery

-0.66

owe

-0.65

orph

-0.64

ethy

-0.64

ety

-0.63

âĻ¦

-0.62

bie

-0.60

 anymore

-0.59

forward

-0.59

POSITIVE LOGITS

 been

1.01

iths

1.01

 originally

0.98

 previously

0.97

 begun

0.97

 hoped

0.95

 undergone

0.94

 initially

0.83

 gotten

0.82

 flown

0.79

Activations Density 0.139%

instances of the word "had."

No Comments

No Known Activations