INDEX

Explanations

mentions of the term "Trump" at various levels of activation strength

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Trump."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

iencies

-0.70

NAD

-0.66

ASA

-0.66

 CentOS

-0.66

 actionGroup

-0.64

SAM

-0.64

 STATS

-0.62

 Mortal

-0.62

RED

-0.61

 Emacs

-0.61

POSITIVE LOGITS

care

1.06

 supporters

0.93

eting

0.92

 Tower

0.91

Jr

0.89

eters

0.88

Care

0.86

eter

0.86

ism

0.82

TRUMP

0.82

Activations Density 0.061%

mentions of the term "Trump" at various levels of activation strength

mentions of the name "Trump."

No Comments

No Known Activations