INDEX

Explanations

mentions of the name "Alon"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Avlon."

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

displayText

-0.78

ORTS

-0.72

natureconservancy

-0.72

 Syri

-0.70

 mathemat

-0.70

ItemTracker

-0.67

ulative

-0.67

 Debor

-0.67

missive

-0.67

¥ŀ

-0.67

POSITIVE LOGITS

naire

1.09

ovan

1.06

ball

0.89

 Luthor

0.86

auts

0.82

agne

0.82

naires

0.80

ning

0.77

ette

0.77

stal

0.76

Activations Density 0.021%

mentions of the name "Alon"

occurrences of the name "Avlon."

No Comments

No Known Activations