INDEX

Explanations

phrases related to machine learning and artificial intelligence

oai_token-act-pair · gpt-3.5-turbo

references to machine learning and artificial intelligence concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Whitman

-0.74

ewater

-0.72

irgin

-0.71

beck

-0.67

swick

-0.67

 Welch

-0.67

Mog

-0.65

ulet

-0.65

kefeller

-0.65

ewitness

-0.64

POSITIVE LOGITS

 algorithms

1.30

 algorithm

1.07

 optimization

0.89

 bots

0.86

onomous

0.85

 analytics

0.80

 systems

0.79

processor

0.78

 processor

0.78

 architectures

0.78

Activations Density 0.053%

phrases related to machine learning and artificial intelligence

references to machine learning and artificial intelligence concepts

No Comments

No Known Activations