INDEX

Explanations

references to the word "new" in various contexts

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

 sqor

-0.83

ascript

-0.82

ONSORED

-0.81

ickr

-0.75

uca

-0.75

OPA

-0.74

iage

-0.74

 actionGroup

-0.72

aminer

-0.72

pless

-0.70

POSITIVE LOGITS

 Zealand

1.35

 Testament

1.21

 York

1.21

 Orleans

1.16

bies

1.13

bie

1.06

 Years

1.03

 Yorker

1.02

 Guinea

1.00

Era

0.99

Activations Density 0.039%

references to the word "new" in various contexts

No Comments

No Known Activations

references to the word "new" in various contexts

No Comments

No Known Activations