INDEX

Explanations

technical specifications or parameters in code or data formats

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

ManagedBean

-0.75

ArgsConstructor

-0.73

mybatisplus

-0.68

Obrázky

-0.60

principalColumn

-0.60

abetes

-0.59

zzleHttp

-0.58

tagHelperRunner

-0.58

 FetchType

-0.57

bodyParser

-0.56

POSITIVE LOGITS

enderror

0.68

 defaultstate

0.66

0.61

↵↵

0.61

“

0.60

\\

0.58

↵

0.56

\\

0.56

}}

0.56

↵↵↵↵

0.56

Activations Density 0.522%

technical specifications or parameters in code or data formats

No Comments

No Known Activations