INDEX

Explanations

words related to strong emotional experiences

oai_token-act-pair · gpt-3.5-turbo

references to emotional states and experiences

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

IFrame

Link

Negative Logits

lust

-0.74

tower

-0.71

essential

-0.70

iago

-0.69

ÄŁ

-0.66

emark

-0.65

llan

-0.65

etting

-0.64

ribution

-0.63

Magazine

-0.63

POSITIVE LOGITS

orically

0.89

 maturity

0.85

 distress

0.80

otional

0.79

 intimacy

0.79

 feelings

0.77

 contag

0.77

 outburst

0.77

 attachment

0.74

orical

0.73

Activations Density 0.016%

words related to strong emotional experiences

references to emotional states and experiences

No Known Activations