INDEX

Explanations

technical terms related to programming or mathematics, particularly focusing on parameters

oai_token-act-pair · gpt-3.5-turbo

terms related to programming parameters and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rup

-0.79

velt

-0.73

urst

-0.71

yt

-0.71

orno

-0.67

wind

-0.67

VIDEO

-0.65

kus

-0.65

cler

-0.64

icago

-0.64

POSITIVE LOGITS

eters

1.14

eter

1.02

ilitary

0.87

 placeholder

0.84

 params

0.82

 parameters

0.81

witz

0.81

etric

0.81

 args

0.81

ules

0.80

Activations Density 0.045%

technical terms related to programming or mathematics, particularly focusing on parameters

terms related to programming parameters and arguments

No Comments

No Known Activations