INDEX

Explanations

phrases related to the spatial positions of objects or points

oai_token-act-pair · gpt-3.5-turbo

phrases or references related to location or position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

dayName

-0.68

etic

-0.66

resy

-0.64

thren

-0.62

-0.59

forts

-0.59

~~~~~~~~~~~~~~~~

-0.58

far

-0.58

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

-0.57

DEN

-0.57

POSITIVE LOGITS

 each

0.86

the

0.84

 town

0.78

 nowhere

0.76

 stairs

0.75

 campus

0.70

rium

0.67

 every

0.67

 chromosomes

0.66

course

0.66

Activations Density 0.111%

phrases related to the spatial positions of objects or points

phrases or references related to location or position

No Comments

No Known Activations