INDEX

Explanations

conditional sentences or phrases indicating exceptions and specific cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

UnusedPrivate

-0.77

writeFieldEnd

-0.76

sidemargin

-0.67

LookAnd

-0.67

mybatisplus

-0.67

posedge

-0.67

}],

-0.67

OGND

-0.65



-0.65

StoryboardSegue

-0.64

POSITIVE LOGITS

 case

3.58

case

3.13

 cases

2.86

Case

2.81

 Case

2.77

 caso

2.71

CASE

2.48

 CASE

2.48

 Cases

2.37

cases

2.35

Activations Density 0.682%

conditional sentences or phrases indicating exceptions and specific cases

No Comments

No Known Activations