INDEX

Explanations

mentions of the location "Los Angeles"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Los Angeles"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 neut

-0.74

 weak

-0.72

gen

-0.68

 fertil

-0.67

fet

-0.66

 trump

-0.65

weak

-0.63

 quantum

-0.63

 breaking

-0.62

 preference

-0.61

POSITIVE LOGITS

 Angeles

3.83

 ANGEL

1.56

 Aires

1.22

 LAPD

1.14

 Orleans

1.14

LA

1.14

 Manila

1.13

 Angels

1.10

Los

1.09

Angel

1.08

Activations Density 0.022%

mentions of the location "Los Angeles"

occurrences of the term "Los Angeles"

No Comments

No Known Activations