INDEX

Explanations

terms related to the legal system, specifically focusing on jurors and judicial proceedings

oai_token-act-pair · gpt-3.5-turbo

references to juries and jurors in the context of legal proceedings

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

PCB

-0.67

 Rail

-0.64

 Pixie

-0.62

!/

-0.62

ORE

-0.61

 Depot

-0.61

 Indian

-0.58

BIG

-0.58

OMG

-0.58

 rooting

-0.58

POSITIVE LOGITS

iscons

1.12

assic

1.00

Jur

0.99

isd

0.97

izons

0.88

jur

0.87

ieu

0.85

iosity

0.85

suit

0.83

istani

0.83

Activations Density 0.012%

terms related to the legal system, specifically focusing on jurors and judicial proceedings

references to juries and jurors in the context of legal proceedings

No Comments

No Known Activations