INDEX

Explanations

proper nouns related to notable individuals or locations

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic locations or entities

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

urat

-0.79

perty

-0.77

arak

-0.74

yip

-0.74

odan

-0.72

atro

-0.68

 Mehran

-0.67

 indo

-0.66

wcs

-0.66

uras

-0.64

POSITIVE LOGITS

sworth

0.85

neum

0.73

gins

0.71

 è£ıè

0.69

beck

0.68

sted

0.68

hyde

0.67

Henry

0.66

enegger

0.65

ettes

0.64

Activations Density 0.213%

proper nouns related to notable individuals or locations

references to specific geographic locations or entities

No Comments

No Known Activations