INDEX

Explanations

specific mentions of ML (machine learning) entities or concepts

oai_token-act-pair · gpt-3.5-turbo

mentions of "ML" (machine learning) in various contexts

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

nces

-0.79

lished

-0.72

ãĥĦ

-0.72

ricular

-0.71

 Wildcats

-0.71

forcing

-0.70

 Gamble

-0.68

ãĥĹ

-0.67

 Normandy

-0.63

=-=-=-=-=-=-=-=-

-0.62

POSITIVE LOGITS

anguage

1.01

ML

0.89

aughter

0.88

arge

0.88

TON

0.86

yrics

0.83

ogy

0.83

iquid

0.83

endon

0.82

ibrary

0.80

Activations Density 0.016%

specific mentions of ML (machine learning) entities or concepts

mentions of "ML" (machine learning) in various contexts

No Comments

No Known Activations