INDEX

Explanations

phrases and terms related to immigration, such as undocumented immigrants, sanctuary cities, deportation, and immigrant populations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MpServer

-0.80

oeuv

-0.78

idges

-0.77

MET

-0.72

apter

-0.71

 Nicotine

-0.71

ilts

-0.69

iac

-0.69

peer

-0.68

 Attribution

-0.68

POSITIVE LOGITS

 visas

1.03

 immigrants

0.98

 visa

0.94

 fleeing

0.92

 deport

0.91

 immigration

0.90

 detention

0.89

 resettlement

0.88

 deported

0.88

 deportation

0.87

Activations Density 2.047%

phrases and terms related to immigration, such as undocumented immigrants, sanctuary cities, deportation, and immigrant populations

No Comments

No Known Activations