INDEX

Explanations

negative words related to unhappiness and poor conditions

oai_token-act-pair · gpt-3.5-turbo

terms associated with negative emotional states or poor conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

•layer 5 - sadness

No Comments

Negative Logits

omen

-0.88

ioch

-0.86

ortium

-0.84

encers

-0.84

icipated

-0.80

tnc

-0.79

encer

-0.78

illance

-0.77

leans

-0.75

natureconservancy

-0.74

POSITIVE LOGITS

 miserable

0.86

 nightmare

0.69

 Goods

0.68

 excuse

0.68

 donkey

0.68

 excuses

0.67

 dismal

0.66

 bastard

0.66

 disappoint

0.65

abama

0.65

Activations Density 0.041%

negative words related to unhappiness and poor conditions

terms associated with negative emotional states or poor conditions

No Comments

No Known Activations