INDEX

Explanations

words or phrases related to technology and innovation, particularly focusing on small or compact forms

oai_token-act-pair · gpt-3.5-turbo

references to miniaturized concepts or objects

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

 foremost

-0.69

 outnumbered

-0.67

 disproportionately

-0.66

aceous

-0.64

 suited

-0.63

 Zimmer

-0.63

 visibly

-0.63

 traditionally

-0.62

 visually

-0.62

 overtly

-0.61

POSITIVE LOGITS

series

1.12

analysis

1.07

batch

1.06

organisms

1.06

government

1.03

gravity

1.03

budget

1.02

dial

1.01

events

1.01

crit

1.01

Activations Density 0.064%

words or phrases related to technology and innovation, particularly focusing on small or compact forms

references to miniaturized concepts or objects

No Comments

No Known Activations