INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flare

-0.63

Zi

-0.63

 Adin

-0.63

sson

-0.61

bour

-0.60

sie

-0.58

existence

-0.57

Ñĭ

-0.57

otine

-0.57

 Carnage

-0.57

POSITIVE LOGITS

 Properties

0.65

 appoint

0.64

anwhile

0.60

 disappro

0.59

 fantas

0.59

 remembers

0.59

 contem

0.59

 latter

0.58

addin

0.58

 strateg

0.58

Activations Density 0.810%

proper nouns related to individuals

proper nouns and names

No Comments

No Known Activations