INDEX

Explanations

mentions of political figures and government actions, particularly related to investigations or requests

oai_token-act-pair · gpt-3.5-turbo

names of political figures and references to political events or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Collective

-0.77

unity

-0.74

edit

-0.68

UE

-0.68

ept

-0.67

 Guides

-0.67

 hindsight

-0.67

vered

-0.66

PK

-0.65

itual

-0.64

POSITIVE LOGITS

alde

0.79

icut

0.69

 deserts

0.68

Jr

0.63

nen

0.63

ASHINGTON

0.61

ORGE

0.60

 outl

0.60

ibia

0.60

taboola

0.60

Activations Density 0.264%

mentions of political figures and government actions, particularly related to investigations or requests

names of political figures and references to political events or entities

No Comments

No Known Activations