INDEX

Explanations

mentions of companies or organizations with the abbreviation "ML"

oai_token-act-pair · gpt-3.5-turbo

references to "ML" or related terms in a context likely involving Machine Learning

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

nces

-0.78

ricular

-0.72

forcing

-0.71

lished

-0.69

til

-0.67

stant

-0.67

hered

-0.66

liest

-0.63

 Normandy

-0.62

rek

-0.60

POSITIVE LOGITS

anguage

0.90

DN

0.89

aughter

0.86

Http

0.85

OGR

0.85

iquid

0.84

ML

0.83

TON

0.82

ibrary

0.80

yrics

0.80

Activations Density 0.026%

mentions of companies or organizations with the abbreviation "ML"

references to "ML" or related terms in a context likely involving Machine Learning

No Comments

No Known Activations