INDEX

Explanations

mentions related to political activism and government policies

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

 partName

-0.75

yssey

-0.74

STAR

-0.72

mir

-0.71

 whirlwind

-0.69

 disappoint

-0.69

optim

-0.66

wow

-0.66

SUM

-0.65

 PROG

-0.65

POSITIVE LOGITS

 prohibited

1.19

 lawfully

1.16

 lawful

1.12

 allowable

1.10

 permissible

1.09

 unlawful

1.09

 permitted

1.04

 exempted

1.03

 exemptions

1.01

 unlawfully

1.00

Activations Density 3.165%

mentions related to political activism and government policies

No Comments

No Known Activations