INDEX

Explanations

mentions of borders, walls, and immigration-related topics

oai_token-act-pair · gpt-3.5-turbo

references to border security and immigration policies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.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

atre

-0.80

bet

-0.80

 Olympus

-0.79

 Shard

-0.79

 Philips

-0.78

VK

-0.78

obyl

-0.77

 Chess

-0.76

 Nikon

-0.76

oult

-0.76

POSITIVE LOGITS

 deport

1.96

 immigration

1.90

 DACA

1.85

 deportation

1.85

 Immigration

1.84

 deported

1.81

 Mexicans

1.80

 Mexican

1.80

 undocumented

1.80

 immigrants

1.73

Activations Density 0.568%

mentions of borders, walls, and immigration-related topics

references to border security and immigration policies

No Comments

No Known Activations