INDEX

Explanations

mentions of legal proceedings

oai_token-act-pair · gpt-3.5-turbo

words related to legal or judicial contexts

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

abee

-0.66

dos

-0.65

 Qiao

-0.65

 Cosponsors

-0.61

allow

-0.60

 Insurance

-0.60

balls

-0.59

washer

-0.59

arantine

-0.59

Gy

-0.58

POSITIVE LOGITS

orescence

0.90

ä»£

0.78

ionage

0.74

 Ital

0.73

hedon

0.73

iage

0.70

olkien

0.69

ength

0.68

×Ļ×

0.67

ACTED

0.66

Activations Density 0.037%

mentions of legal proceedings

words related to legal or judicial contexts

No Comments

No Known Activations