INDEX

Explanations

mentions of or related to the former U.S. President Donald Trump

oai_token-act-pair · gpt-3.5-turbo

references to President Donald Trump

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Mortal

-0.70

ANA

-0.67

NAD

-0.65

PsyNetMessage

-0.65

çĶ°

-0.64

ASA

-0.64

iencies

-0.62

 Emacs

-0.62

SAM

-0.61

 fiber

-0.61

POSITIVE LOGITS

care

0.98

 Donald

0.90

TRUMP

0.80

Jr

0.80

Trump

0.80

omics

0.80

 appoint

0.79

ism

0.78

 Trump

0.77

Care

0.77

Activations Density 0.058%

mentions of or related to the former U.S. President Donald Trump

references to President Donald Trump

No Comments

No Known Activations