INDEX

Explanations

concepts and terms related to psychological theories and their applications in research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

postIndex

-0.56

MethodManager

-0.49

extraction

-0.47

resizingMask

-0.47

+#+

-0.46

AutoresizingMask

-0.45

GIVEREF

-0.45

UpInside

-0.45

ServletException

-0.44

 дорого

-0.44

POSITIVE LOGITS

 theory

0.72

 Theory

0.60

Theory

0.57

 Theorie

0.56

 theories

0.56

 hypothesis

0.54

 teori

0.54

 théorie

0.54

 teoria

0.53

 teoría

0.53

Activations Density 0.688%

concepts and terms related to psychological theories and their applications in research

No Comments

No Known Activations