INDEX

Explanations

references to specific locations or establishments, particularly with the word "Village" in them

oai_token-act-pair · gpt-3.5-turbo

mentions of specific places, particularly "Village."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

cies

-0.83

ĻĤ

-0.81

iscopal

-0.80

cffff

-0.78

cific

-0.78

etr

-0.77

ional

-0.76

odynam

-0.76

arching

-0.75

etrical

-0.74

POSITIVE LOGITS

 Village

1.29

 Plaza

0.96

 Massacre

0.94

 Taxi

0.89

 Clinic

0.89

 Improvement

0.86

 Island

0.86

 Vanguard

0.86

 Voice

0.84

 Weekend

0.84

Activations Density 0.011%

references to specific locations or establishments, particularly with the word "Village" in them

mentions of specific places, particularly "Village."

No Comments

No Known Activations