INDEX

Explanations

information related to storytelling, movies, and specific 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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dayName

-0.67

rop

-0.65

 Patri

-0.57

 guiActiveUn

-0.57

DragonMagazine

-0.56

Jem

-0.54

AUD

-0.54

Pag

-0.54

 Foss

-0.53

uyomi

-0.52

POSITIVE LOGITS

1.18

1.16

1.15

1.14

1.12

1.11

Activations Density 2.910%

information related to storytelling, movies, and specific events

No Comments

No Known Activations