INDEX

Explanations

mentions of specific inclusions or exclusions in a list

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "included" or its variations

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

 temper

-0.74

 climates

-0.72

thur

-0.71

ingham

-0.67

ggles

-0.65

²¾

-0.65

aptic

-0.64

anship

-0.64

redo

-0.64

\\\\\\\\

-0.64

POSITIVE LOGITS

 herein

0.81

 prominently

0.80

ãĤ´

0.79

ãģĨ

0.75

atinum

0.70

 Included

0.68

 Include

0.68

 therein

0.68

rescent

0.66

ropolitan

0.65

Activations Density 0.041%

mentions of specific inclusions or exclusions in a list

occurrences of the word "included" or its variations

No Comments

No Known Activations