INDEX

Explanations

code-related syntax, particularly in relation to function definitions and method calls

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

*)((

-0.59

SerializedName

-0.57

خواندن

-0.57

 Ballard

-0.57

ย์

-0.55

ciamento

-0.55

ZZLE

-0.53

 Nebel

-0.53

 Findlay

-0.53

 BaseModel

-0.52

POSITIVE LOGITS

 مرئيه

0.76

いる

0.68

setVerticalGroup

0.68

 springfox

0.65

zwischen

0.65

WireFormatLite

0.63

 Sosa

0.62

Huhu

0.62

ğraf

0.61

 Autorisations

0.60

Activations Density 0.402%

code-related syntax, particularly in relation to function definitions and method calls

No Comments

No Known Activations