INDEX

Explanations

abbreviations related to medical terms

oai_token-act-pair · gpt-3.5-turbo

references to the term "DR" related to medical or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ropolitan

-0.76

 Pose

-0.70

eers

-0.67

 Corpus

-0.67

 ç¥ŀ

-0.66

rament

-0.65

 Wildcats

-0.63

chio

-0.62

ria

-0.62

mate

-0.62

POSITIVE LOGITS

ESS

0.97

INK

0.94

OME

0.92

IVERS

0.92

IVE

0.89

inks

0.86

inking

0.85

ESH

0.83

adeon

0.81

ength

0.79

Activations Density 0.005%

abbreviations related to medical terms

references to the term "DR" related to medical or technical contexts

No Comments

No Known Activations