INDEX

Explanations

references to opinions or positions held on various issues

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

NetMessage

-1.11

STON

-0.75

batch

-0.74

duct

-0.70

 Sabha

-0.67

 Towers

-0.67

issance

-0.65

ãĥ¼ãĥĨãĤ£

-0.65

Osc

-0.63

Sample

-0.63

POSITIVE LOGITS

 stance

1.29

 stances

1.24

 toward

1.03

 towards

1.00

 regarding

0.95

 positions

0.89

 views

0.88

 against

0.86

 favoring

0.83

 viewpoint

0.82

Activations Density 0.018%

references to opinions or positions held on various issues

No Comments

No Known Activations