INDEX

Explanations

nothing, as it has zero activations across all inputs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Signalez

-0.61

 للمعارف

-0.59

IContainer

-0.57

NewUrlParser

-0.55

 Bruch

-0.55

الدراسه

-0.55

SequentialGroup

-0.55

enumi

-0.55

rungsseite

-0.54

 AttributeSet

-0.54

POSITIVE LOGITS

IUrlHelper

1.41

发表于

0.53

addCriterion

0.53

exitRule

0.48

 esetén

0.47

protoc

0.47

itorious

0.46

AutoScaleMode

0.46

scrolling

0.45

posium

0.44

Activations Density 0.012%

nothing, as it has zero activations across all inputs

No Comments

No Known Activations