INDEX

Explanations

specific dates in various formats

oai_token-act-pair · gpt-3.5-turbo

specific years or dates mentioned in the text

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

amins

-0.67

 plur

-0.66

 endless

-0.65

onite

-0.62

 Wonders

-0.61

ousel

-0.59

advertisement

-0.59

outer

-0.58

und

-0.57

 noisy

-0.56

POSITIVE LOGITS

displayText

0.69

 Referred

0.67

mr

0.67

isSpecialOrderable

0.67

UTC

0.66

âĸĪ

0.66

 Miko

0.65

âĢ²

0.63

âĢİ

0.63

RHP

0.63

Activations Density 0.055%

specific dates in various formats

specific years or dates mentioned in the text

No Comments

No Known Activations