INDEX

Explanations

references to physical or digital banners

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "banner" 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 @ 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

urrency

-0.74

lege

-0.74

ulu

-0.72

cephal

-0.69

nesota

-0.67

sis

-0.67

AE

-0.67

OTOS

-0.65

iott

-0.62

esters

-0.62

POSITIVE LOGITS

 banner

1.04

 banners

1.03

pole

0.96

boards

0.87

 proclaiming

0.85

strip

0.82

board

0.79

holder

0.77

ged

0.76

staff

0.76

Activations Density 0.028%

references to physical or digital banners

occurrences of the word "banner" and its variations

No Comments

No Known Activations