INDEX

Explanations

phrases or sentences indicating a scenario or comparison

oai_token-act-pair · gpt-3.5-turbo

conditional phrases that describe hypothetical situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Saskatchewan

-0.70

âī

-0.69

JC

-0.68

istries

-0.67

 Reno

-0.67

 Dragons

-0.67

»Ĵ

-0.66

 âĨ

-0.66

\/\/

-0.65

UCK

-0.65

POSITIVE LOGITS

 insin

0.68

 confir

0.66

anwhile

0.66

yip

0.65

heit

0.65

liest

0.65

pmwiki

0.64

 dictated

0.64

lamm

0.63

govtrack

0.61

Activations Density 0.091%

phrases or sentences indicating a scenario or comparison

conditional phrases that describe hypothetical situations

No Comments

No Known Activations