INDEX

Explanations

references to food and physical actions, such as eating and moving

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

anism

-0.92

evidence

-0.74

peak

-0.71

grounds

-0.70

iments

-0.70

Edit

-0.68

agree

-0.68

 matters

-0.67

Autom

-0.66

tm

-0.65

POSITIVE LOGITS

lot

1.37

 bunch

1.31

 handful

1.24

 couple

1.22

few

1.16

 whopping

1.14

 plethora

1.12

 slew

1.11

 dozen

1.06

bit

1.02

Activations Density 1.464%

references to food and physical actions, such as eating and moving

No Comments

No Known Activations