INDEX

Explanations

phrases indicating distance or location

oai_token-act-pair · gpt-3.5-turbo

references to distance or proximity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ammy

-0.84

oly

-0.77

ums

-0.74

annis

-0.72

xual

-0.71

ionic

-0.71

anwhile

-0.71

elly

-0.71

igel

-0.71

 Zeit

-0.70

POSITIVE LOGITS

 away

0.83

away

0.72

 Away

0.71

ADRA

0.69

ĳå£«

0.68

 waivers

0.68

à©

0.67

 Territories

0.67

doors

0.66

RAG

0.66

Activations Density 0.027%

phrases indicating distance or location

references to distance or proximity

No Comments

No Known Activations