INDEX

Explanations

phrases related to the location "Washington, DC."

oai_token-act-pair · gpt-3.5-turbo

references to locations, specifically Washington D.C. and its associated elements

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

INAL

-0.76

rophe

-0.74

restrial

-0.67

ãĤ¶

-0.67

(<

-0.67

è¦ļéĨĴ

-0.67

ogram

-0.67

milo

-0.67

 Donation

-0.67

emi

-0.66

POSITIVE LOGITS

 Barrett

0.70

 Toll

0.70

owitz

0.69

ipeg

0.69

 Stra

0.69

wagen

0.68

 bureau

0.68

zyk

0.66

 Kashmir

0.66

 Doyle

0.66

Activations Density 0.111%

phrases related to the location "Washington, DC."

references to locations, specifically Washington D.C. and its associated elements

No Comments

No Known Activations