INDEX

Explanations

occurrences of "dot" in mathematical or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-1.06

 Jefus

-1.01

Efq

-1.01

 myſelf

-1.00

ſelves

-0.99

 Theſe

-0.98

 themſelves

-0.98

 houſe

-0.95

 juſ

-0.95

 Houſe

-0.94

POSITIVE LOGITS

dot

1.25

dot

1.11

dots

0.84

Dot

0.82

Dot

0.80

 متعلقه

0.71

DOT

0.69

 dots

0.66

od

0.62

ddot

0.62

Activations Density 0.126%

occurrences of "dot" in mathematical or programming contexts

No Comments

No Known Activations