INDEX

Explanations

political and legislative references

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

obal

-0.82

uga

-0.79

iosyn

-0.79

otos

-0.72

actionDate

-0.71

ahon

-0.70

ULAR

-0.69

ordable

-0.68

imentary

-0.68

 horm

-0.68

POSITIVE LOGITS

 syndrome

1.16

 Syndrome

1.06

âĦ¢

1.02

 Ratio

0.96

!,

0.96

 ratio

0.90

 fallacy

0.84

 fame

0.83

 trope

0.79

!.

0.78

Activations Density 3.349%

political and legislative references

No Comments

No Known Activations