INDEX

Explanations

words related to a specific fictional character or concept

oai_token-act-pair · gpt-3.5-turbo

references to people with the name "inger" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aiman

-0.83

iries

-0.77

ccording

-0.71

anus

-0.69

urus

-0.68

ÅĤ

-0.68

igm

-0.68

anism

-0.67

BuyableInstoreAndOnline

-0.66

ategory

-0.66

POSITIVE LOGITS

glass

0.86

bread

0.84

writer

0.78

mond

0.78

wcs

0.77

maid

0.76

butt

0.70

writers

0.69

 seeker

0.68

felt

0.67

Activations Density 0.026%

words related to a specific fictional character or concept

references to people with the name "inger" or variations of it

No Comments

No Known Activations