INDEX

Explanations

phrases related to legal terms and law enforcement

oai_token-act-pair · gpt-3.5-turbo

terms related to legal or governmental authority

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

URA

-0.82

Course

-0.76

Ò

-0.75

Newsletter

-0.73

bite

-0.73

LV

-0.72

ITCH

-0.72

RS

-0.72

DAQ

-0.72

Hidden

-0.71

POSITIVE LOGITS

olic

1.21

ity

1.03

chio

0.99

ulum

0.85

itionally

0.84

jriwal

0.83

enza

0.83

 acid

0.80

ities

0.80

ipop

0.80

Activations Density 0.013%

phrases related to legal terms and law enforcement

terms related to legal or governmental authority

No Comments

No Known Activations