INDEX

Explanations

terms related to government and institutions

oai_token-act-pair · gpt-3.5-turbo

terms related to government, its agencies, and associated policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.60

ldom

-0.60

é¾įå

-0.60

ividual

-0.60

sic

-0.59

æµ

-0.57

ãĥĩãĤ£

-0.56

âĸ¬

-0.56

ãĥ¼ãĥĨãĤ£

-0.55

@@@@

-0.54

POSITIVE LOGITS

 astronomers

0.58

 officer

0.55

 analyst

0.54

 justice

0.54

 investigator

0.54

 analysts

0.52

 watchdog

0.52

MPG

0.51

 officials

0.50

 scientists

0.50

Activations Density 0.694%

terms related to government and institutions

terms related to government, its agencies, and associated policies

No Comments

No Known Activations