INDEX

Explanations

words related to food items, specifically pizza and related terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "pizza."

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

 Niet

-0.73

 newcom

-0.64

 bystand

-0.62

ITNESS

-0.58

QC

-0.58

Qual

-0.58

 Alam

-0.56

 Territories

-0.56

Social

-0.56

CLASS

-0.56

POSITIVE LOGITS

hare

1.13

poons

1.04

etting

1.03

hips

1.02

hip

1.01

mith

1.01

cale

1.01

hell

0.99

avers

0.99

igmatic

0.98

Activations Density 0.176%

words related to food items, specifically pizza and related terms

occurrences of the word "pizza."

No Comments

No Known Activations