INDEX

Explanations

references to psychological conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

IndentedString

-0.79

hematical

-0.77

ValueStyle

-0.75

CloseOperation

-0.74

béco

-0.67

parsedMessage

-0.67

nonatomic

-0.67

providedIn

-0.66

WHO

-0.66

 Reverso

-0.66

POSITIVE LOGITS

 Ferri

0.57

 ITIS

0.57

})));

0.56

 lines

0.54

 LINES

0.52

ehe

0.52

 Preußen

0.52

ist

0.51

ky

0.51

 umgekehrt

0.51

Activations Density 0.015%

references to psychological conditions

No Comments

No Known Activations