INDEX

Explanations

occurrences of the term "Cal"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 nahilalakip

-0.60

DockStyle

-0.59

denly

-0.54

ępo

-0.54

intellij

-0.52

綜合報導

-0.52

 Ciudad

-0.51

 الاص

-0.51

DECREF

-0.50

 RouterModule

-0.50

POSITIVE LOGITS

cal

3.44

Cal

3.39

Cal

3.27

cal

3.10

CAL

3.03

CAL

2.81

 calc

2.29

kal

2.23

 Calc

2.12

Kal

2.03

Activations Density 0.081%

occurrences of the term "Cal"

No Comments

No Known Activations