INDEX

Explanations

quantitative statements 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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

omics

-0.77

 brainstorm

-0.72

itory

-0.72

 footing

-0.71

 allocation

-0.71

 assignment

-0.71

plet

-0.68

 sprint

-0.68

 intervention

-0.68

 restructuring

-0.67

POSITIVE LOGITS

 Known

1.50

Its

1.40

 Occasionally

1.38

 Additionally

1.35

 However

1.32

 Recently

1.27

 Approximately

1.26

 Nevertheless

1.25

 Interestingly

1.24

 Also

1.23

Activations Density 0.508%

quantitative statements or statistics

No Comments

No Known Activations