INDEX

Explanations

words related to emotions or feelings, specifically focusing on the concept of 'mood'

oai_token-act-pair · gpt-3.5-turbo

references to emotional states and moods

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ded

-0.71

ces

-0.69

 Universities

-0.68

 WATCHED

-0.67

 Highlander

-0.66

ced

-0.66

xton

-0.65

cing

-0.65

chnology

-0.62

pta

-0.62

POSITIVE LOGITS

 mood

1.04

 Mood

0.84

 contag

0.78

0.77

 swings

0.75

iness

0.73

 stabil

0.72

achine

0.72

 conducive

0.71

 disorder

0.69

Activations Density 0.024%

words related to emotions or feelings, specifically focusing on the concept of 'mood'

references to emotional states and moods

No Comments

No Known Activations