INDEX

Explanations

phrases related to legal actions or law enforcement

oai_token-act-pair · gpt-3.5-turbo

sentences, particularly those expressing opinions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 tremend

-0.81

 therap

-0.78

 carbohyd

-0.78

 elig

-0.78

 volunte

-0.78

 skelet

-0.76

 warr

-0.71

 affili

-0.71

 bidder

-0.70

tyr

-0.70

POSITIVE LOGITS

 Thankfully

1.30

 Whether

1.30

 However

1.27

 Luckily

1.27

But

1.25

 Fortunately

1.24

 Unfortunately

1.22

 Sure

1.19

 Often

1.18

 Usually

1.17

Activations Density 0.511%

phrases related to legal actions or law enforcement

sentences, particularly those expressing opinions or statements

No Comments

No Known Activations