INDEX

Explanations

references to the year 2009

oai_token-act-pair · gpt-3.5-turbo

references to the year 2009

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

onite

-0.84

onal

-0.71

phia

-0.67

kef

-0.67

alty

-0.66

Magikarp

-0.62

hma

-0.62

orable

-0.62

avis

-0.61

vere

-0.61

POSITIVE LOGITS

å¹

1.04

-'

0.86

 onwards

0.78

0.72

0.69

âĢ²

0.67

 onward

0.65

0.63

Activations Density 0.021%

references to the year 2009

references to the year 2009

No Comments

No Known Activations