INDEX

Explanations

specific political figures and their respective locations or affiliations

oai_token-act-pair · gpt-3.5-turbo

political party affiliations and their designations in a legislative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rhy

-0.77

 provocation

-0.77

obyl

-0.73

 intrinsic

-0.72

 ransom

-0.71

 structure

-0.70

 mathematic

-0.68

 maturity

-0.68

 explorers

-0.67

llah

-0.67

POSITIVE LOGITS

California

1.00

Minnesota

1.00

NV

0.97

Wisconsin

0.97

CA

0.94

Michigan

0.94

)'

0.94

Virginia

0.94

MN

0.94

Rh

0.93

Activations Density 0.035%

specific political figures and their respective locations or affiliations

political party affiliations and their designations in a legislative context

No Comments

No Known Activations