INDEX

Explanations

phrases related to educational or academic settings

oai_token-act-pair · gpt-3.5-turbo

words related to scientific classifications or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ierrez

-0.86

efully

-0.67

inyl

-0.67

acca

-0.64

Winged

-0.64

ually

-0.62

igators

-0.61

engers

-0.60

igated

-0.60

externalActionCode

-0.60

POSITIVE LOGITS

ng

0.92

clinton

0.81

 gland

0.75

sburg

0.69

otic

0.69

ansas

0.68

deen

0.67

 glands

0.67

rha

0.67

otes

0.66

Activations Density 0.052%

phrases related to educational or academic settings

words related to scientific classifications or categories

No Comments

No Known Activations