INDEX

Explanations

phrases related to specific locations or events

oai_token-act-pair · gpt-3.5-turbo 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

"!

-0.71

udos

-0.63

 attRot

-0.63

OLOG

-0.59

PAN

-0.58

PAC

-0.56

Foot

-0.56

cellaneous

-0.56

inline

-0.56

 ACTIONS

-0.54

POSITIVE LOGITS

 versus

1.01

("

0.77

(),

0.74

 outweigh

0.70

vs

0.70

and

0.67

})

0.66

*/(

0.65

('

0.65

?,

0.63

Activations Density 0.633%

phrases related to specific locations or events

No Comments

No Known Activations