INDEX

Explanations

proper nouns related to a specific name or entity, particularly 'Mun' variations

oai_token-act-pair · gpt-3.5-turbo

references to the term "Mun" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

soDeliveryDate

-0.70

ylum

-0.69

ãĤ¼

-0.68

toe

-0.68

 Oriental

-0.64

 Tsukuyomi

-0.64

ä»£

-0.64

orical

-0.63

opher

-0.62

 Madden

-0.62

POSITIVE LOGITS

ificent

1.04

roe

0.97

Mun

0.96

nel

0.96

itionally

0.90

geon

0.87

caster

0.84

oons

0.81

awar

0.79

ster

0.79

Activations Density 0.005%

proper nouns related to a specific name or entity, particularly 'Mun' variations

references to the term "Mun" in various contexts

No Comments

No Known Activations