INDEX

Explanations

phrases related to judgment and perception of actions or situations

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

 ãĢĮ

-0.75

 ï¿½

-0.74

 ---------

-0.68

arnaev

-0.65

essage

-0.65

 Â«

-0.56

ometimes

-0.55

Phys

-0.54

 Â§Â§

-0.54

 ----------------

-0.53

POSITIVE LOGITS

1.83

"?

1.75

",

1.71

".

1.70

"—

1.68

"!

1.63

".[

1.63

":

1.58

"âĢ¦

1.56

%"

1.55

Activations Density 0.772%

phrases related to judgment and perception of actions or situations

No Comments

No Known Activations