INDEX

Explanations

references to theoretical frameworks or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 οποία

-0.68

 NavController

-0.66

ombus

-0.64

 communic

-0.62

 république

-0.62

vgl

-0.61

VIV

-0.61

 Bist

-0.61

 Tremb

-0.61

ctiveness

-0.60

POSITIVE LOGITS

 theory

1.96

 theories

1.92

theory

1.83

 Theory

1.81

 THEORY

1.79

Theory

1.73

THEORY

1.69

 Theories

1.63

 theorists

1.43

 teoría

1.35

Activations Density 0.086%

references to theoretical frameworks or concepts

No Comments

No Known Activations