INDEX

Explanations

references to theories and theoretical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.66

frid

-0.61

igshid

-0.61

ccb

-0.60

 NavController

-0.59

 Bist

-0.59

ombus

-0.59

VIV

-0.58

IBarButtonItem

-0.58

 amarillas

-0.58

POSITIVE LOGITS

 theories

1.33

 Theories

1.17

 theory

1.15

THEORY

1.11

 THEORY

1.09

 Theory

1.08

theory

1.08

Theory

1.03

 Theor

0.94

 theorists

0.92

Activations Density 0.092%

references to theories and theoretical concepts

No Comments

No Known Activations