INDEX

Explanations

terms related to receiving attention or recognition

oai_token-act-pair · gpt-3.5-turbo

terms associated with receiving or acquiring attention, support, or feedback

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

idia

-0.71

 contrace

-0.68

pci

-0.66

 Coliseum

-0.62

 Relax

-0.62

wine

-0.61

 converter

-0.60

 trave

-0.59

 raping

-0.59

 starve

-0.57

POSITIVE LOGITS

 headlines

0.96

 rave

0.89

 widespread

0.84

 attention

0.84

 notoriety

0.84

 scrutiny

0.80

 merit

0.77

osponsors

0.77

 comparisons

0.76

 critics

0.75

Activations Density 0.222%

terms related to receiving attention or recognition

terms associated with receiving or acquiring attention, support, or feedback

No Comments

No Known Activations