INDEX

Explanations

instances of people or things returning to a place or activity

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "return" and its variations

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

ussen

-0.70

vern

-0.70

boss

-0.68

hemat

-0.67

warts

-0.67

Cola

-0.66

cape

-0.66

 gauge

-0.64

astics

-0.63

agram

-0.63

POSITIVE LOGITS

 home

0.90

ees

0.85

 HOME

0.78

home

0.74

 postage

0.72

 safely

0.71

owship

0.71

 Returning

0.70

porting

0.68

 victorious

0.67

Activations Density 0.028%

instances of people or things returning to a place or activity

occurrences of the word "return" and its variations

No Comments

No Known Activations