INDEX

Explanations

references to people and individuals in various contexts

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

Accessory

-0.80

Operation

-0.78

 srfAttach

-0.75

Solution

-0.73

tnc

-0.73

inventoryQuantity

-0.72

COMPLE

-0.70

catentry

-0.70

\/\/

-0.67

 Butt

-0.65

POSITIVE LOGITS

 smugglers

1.12

folk

1.08

who

1.08

hood

0.92

 born

0.86

opausal

0.85

 harmed

0.84

 addicted

0.83

 else

0.82

 traffickers

0.81

Activations Density 1.175%

references to people and individuals in various contexts

No Comments

No Known Activations