INDEX

Explanations

words related to diplomatic actions and international sanctions

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

swick

-0.79

uscript

-0.78

ITNESS

-0.74

omorph

-0.69

NAS

-0.67

igel

-0.66

 Bucc

-0.65

 liter

-0.64

omorphic

-0.64

ocent

-0.63

POSITIVE LOGITS

 imposed

1.29

 levied

1.18

 punitive

1.10

 targeting

1.09

 regimes

1.08

 enforced

1.05

 crackdown

1.05

 regime

1.04

 prohibiting

1.00

 enforcement

0.99

Activations Density 1.855%

words related to diplomatic actions and international sanctions

No Comments

No Known Activations