INDEX

Explanations

nested structures in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 disambiguazione

-0.69

enterOuterAlt

-0.69

 astore

-0.67

AddTagHelper

-0.61

<bos>

-0.58

EnableWeb

-0.58

 istore

-0.58

 насељу

-0.57

IContainer

-0.56

 initComponents

-0.53

POSITIVE LOGITS

NavController

0.78

CloseOperation

0.77

 endregion

0.61

enumi

0.60

)++;

0.56

_();

0.55

corazón

0.55

++

0.54

quium

0.53

!")

0.53

Activations Density 0.027%

nested structures in code

No Comments

No Known Activations