INDEX

Explanations

legal terms and court-related phrases

oai_token-act-pair · gpt-3.5-turbo

the use of the phrase "in" related to legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

%%

-0.74

 learners

-0.72

 hooks

-0.69

issance

-0.69

 sensations

-0.68

 ingred

-0.66

 grows

-0.65

 floats

-0.65

 VIDEOS

-0.64

 creeps

-0.63

POSITIVE LOGITS

 lieu

1.31

 favor

1.19

 accordance

1.18

patient

1.14

 conjunction

1.11

ordinate

1.10

 vitro

1.07

 order

1.04

humane

1.01

escap

0.98

Activations Density 0.521%

legal terms and court-related phrases

the use of the phrase "in" related to legal contexts

No Comments

No Known Activations