INDEX

Explanations

proper nouns relating to locations or names

oai_token-act-pair · gpt-3.5-turbo

words related to geographic locations or names

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

avorite

-0.70

DragonMagazine

-0.68

Ö¼

-0.67

 opio

-0.64

 externalToEVAOnly

-0.64

Quote

-0.63

Balt

-0.63

hospital

-0.62

Rot

-0.61

encrypted

-0.61

POSITIVE LOGITS

ovic

0.78

ieri

0.77

ouver

0.77

cules

0.74

ihilation

0.69

ufact

0.67

iens

0.67

atown

0.67

addin

0.66

ioned

0.65

Activations Density 0.144%

proper nouns relating to locations or names

words related to geographic locations or names

No Comments

No Known Activations