INDEX

Explanations

words related to negative experiences or emotions, particularly suffering and confrontation

oai_token-act-pair · gpt-3.5-turbo

concepts related to suffering and confrontation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ItemTracker

-0.76

uyomi

-0.69

>>\

-0.67

fml

-0.62

srf

-0.61

 afore

-0.59

cffffcc

-0.58

 previously

-0.58

 externalToEVAOnly

-0.57

avascript

-0.57

POSITIVE LOGITS

ings

1.54

ments

1.29

ables

1.26

able

1.22

ingly

1.20

ers

1.09

INGS

1.08

backs

1.06

ties

1.02

ership

1.02

Activations Density 0.209%

words related to negative experiences or emotions, particularly suffering and confrontation

concepts related to suffering and confrontation

No Comments

No Known Activations