INDEX

Explanations

mathematical terms and concepts, particularly related to Bayesian statistics and probability distributions

oai_token-act-pair · gpt-3.5-turbo

terms related to Bayesian statistics and probabilistic modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 whistlebl

-0.79

 Kuwait

-0.71

 Dempsey

-0.71

 cringe

-0.69

 hostilities

-0.68

 Veteran

-0.68

 perks

-0.68

 adren

-0.68

laun

-0.67

 Voices

-0.67

POSITIVE LOGITS

 theorem

1.43

\(\

1.18

 algebra

1.16

ensional

1.13

 equations

1.11

$\

1.11

 Mathemat

1.10

orem

1.06

\(

1.05

 mathematic

1.04

Activations Density 0.481%

mathematical terms and concepts, particularly related to Bayesian statistics and probability distributions

terms related to Bayesian statistics and probabilistic modeling

No Comments

No Known Activations