INDEX

Explanations

mentions of specific events or locations

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

AAC

-0.71

Ort

-0.70

 casting

-0.69

 elevation

-0.68

 Petro

-0.68

 Handbook

-0.68

 Britann

-0.68

 cutting

-0.67

 capacity

-0.66

 indirect

-0.66

POSITIVE LOGITS

enough

1.33

shit

1.23

too

1.22

matter

1.17

your

1.17

anything

1.17

needed

1.16

distance

1.14

same

1.14

else

1.14

Activations Density 0.072%

mentions of specific events or locations

No Comments

No Known Activations