INDEX

Explanations

weights given to various aspects or entities

oai_token-act-pair · gpt-3.5-turbo

concepts related to efforts, weight, and importance in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Avenger

-0.67

 lookout

-0.67

 cowork

-0.63

wagen

-0.62

ãĤ´ãĥ³

-0.59

CHAT

-0.59

 Massacre

-0.58

 operative

-0.57

 quint

-0.57

POSITIVE LOGITS

flex

0.91

NH

0.77

 than

0.75

fulness

0.73

aic

0.72

 nowadays

0.71

 mileage

0.67

enance

0.67

 whatsoever

0.66

idious

0.66

Activations Density 0.278%

weights given to various aspects or entities

concepts related to efforts, weight, and importance in discussions

No Comments

No Known Activations