INDEX

Explanations

phrases related to the individual Donald Trump

oai_token-act-pair · gpt-3.5-turbo

mentions of Donald Trump

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

ORED

-0.75

ANA

-0.71

++++

-0.71

SAM

-0.68

++++++++++++++++

-0.68

FU

-0.67

NAD

-0.65

meaning

-0.65

ENCY

-0.64

BILITY

-0.63

POSITIVE LOGITS

Jr

0.99

 Donald

0.86

 Simulator

0.81

 campaigned

0.80

ivari

0.79

ovich

0.78

lda

0.75

enhagen

0.74

legate

0.74

igon

0.74

Activations Density 0.044%

phrases related to the individual Donald Trump

mentions of Donald Trump

No Comments

No Known Activations