INDEX

Explanations

mentions of premium items or services

oai_token-act-pair · gpt-3.5-turbo

references to premium products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

advertisement

-0.77

Ĵ

-0.74

lda

-0.68

****************

-0.67

arms

-0.65

DEC

-0.65

 Epstein

-0.62

=-=-=-=-

-0.62

 Cornell

-0.62

adr

-0.61

POSITIVE LOGITS

 Premium

1.05

raviolet

0.99

 Seym

0.87

 citiz

0.86

 confir

0.84

ature

0.83

rats

0.83

tarian

0.81

ModLoader

0.78

iership

0.78

Activations Density 0.007%

mentions of premium items or services

references to premium products or services

No Comments

No Known Activations