INDEX

Explanations

names of individuals, particularly in pairs or groups

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals and their roles or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

worm

-0.70

arah

-0.65

rina

-0.63

afety

-0.63

ographer

-0.62

teness

-0.60

itiz

-0.59

=/

-0.59

":"/

-0.58

:/

-0.58

POSITIVE LOGITS

 respectively

2.34

 respective

1.38

 jointly

1.29

 alike

1.20

 together

1.14

both

1.13

together

1.06

 apiece

1.05

 Together

0.99

 mutually

0.98

Activations Density 0.678%

names of individuals, particularly in pairs or groups

references to specific individuals and their roles or achievements

No Comments

No Known Activations