INDEX

Explanations

names of geographical locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names related to individuals and organizations

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

ulhu

-0.74

 Archdemon

-0.71

arcity

-0.61

roach

-0.61

behind

-0.60

MAC

-0.60

healthy

-0.59

OPLE

-0.59

ournals

-0.58

rers

-0.58

POSITIVE LOGITS

eton

0.81

etric

0.75

achev

0.73

ibrary

0.70

kov

0.70

tes

0.69

×¨

0.68

oxide

0.67

pg

0.65

beck

0.65

Activations Density 0.249%

names of geographical locations

proper nouns and names related to individuals and organizations

No Comments

No Known Activations