INDEX

Explanations

sophisticated terminology related to argumentation and logical reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

IE

-0.41

hies

-0.41

‚¬

-0.39

 volume

-0.38

nière

-0.37

róż

-0.36

Li

-0.36

scheme

-0.36

сма

-0.36

хал

-0.35

POSITIVE LOGITS

ChildScrollView

0.94

#+#

0.92

 GenerationType

0.91

InputBorder

0.88

 виправивши

0.86

 HasFactory

0.85

MessageOf

0.83

AutoScaleMode

0.83

+#+#

0.81

 صوتيه

0.78

Activations Density 0.945%

sophisticated terminology related to argumentation and logical reasoning

No Comments

No Known Activations