INDEX

Explanations

references to a wide range of different types or forms of something

oai_token-act-pair · gpt-3.5-turbo

the concept of variety in different contexts

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

roit

-0.81

robe

-0.81

thur

-0.71

jin

-0.69

venture

-0.69

avement

-0.68

amina

-0.67

ossier

-0.66

reon

-0.65

onds

-0.65

POSITIVE LOGITS

 Flavoring

0.83

ensical

0.78

 Variety

0.77

 variety

0.75

icult

0.75

 thereof

0.71

 assortment

0.71

istries

0.71

 incarn

0.68

 ways

0.67

Activations Density 0.022%

references to a wide range of different types or forms of something

the concept of variety in different contexts

No Comments

No Known Activations