INDEX

Explanations

phrases related to legal and policy matters

oai_token-act-pair · gpt-3.5-turbo

legislative language and terms related to laws and policies

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

 Atmosp

-0.71

Ltd

-0.64

 Passion

-0.62

 IMAGES

-0.62

 Ples

-0.60

Cam

-0.59

 Shang

-0.58

swick

-0.56

edin

-0.56

 gigs

-0.56

POSITIVE LOGITS

rote

0.84

 abol

0.83

hemy

0.81

 repealing

0.81

 protections

0.77

enei

0.75

 outlaw

0.74

DonaldTrump

0.74

otom

0.70

yrinth

0.70

Activations Density 0.354%

phrases related to legal and policy matters

legislative language and terms related to laws and policies

No Comments

No Known Activations