INDEX

Explanations

specific keywords related to specific entities or concepts, potentially related to economics, politics, or technology

oai_token-act-pair · gpt-3.5-turbo

proper nouns and significant organizations or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uner

-0.80

ads

-0.69

chery

-0.68

aith

-0.68

YL

-0.68

legram

-0.67

lesh

-0.65

renches

-0.65

ridor

-0.65

ilet

-0.65

POSITIVE LOGITS

 bestowed

0.69

 deem

0.68

 deems

0.68

 dear

0.67

 marketers

0.66

 possessed

0.64

 magician

0.64

 desired

0.63

 afforded

0.63

 dearly

0.63

Activations Density 0.296%

specific keywords related to specific entities or concepts, potentially related to economics, politics, or technology

proper nouns and significant organizations or entities

No Comments

No Known Activations