INDEX

Explanations

occurrences of the word "inform" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

لينكات

-0.78

locene

-0.61

netbeans

-0.61

endmodule

-0.60

orneys

-0.60

 BoxDecoration

-0.57

 worshi

-0.55

atyw

-0.54

ándor

-0.54

mtable

-0.54

POSITIVE LOGITS

 inform

2.91

 informed

2.76

 informs

2.70

 informing

2.56

 Informed

2.54

 Inform

2.50

Inform

2.49

informed

2.38

 INFORM

2.36

inform

2.35

Activations Density 0.102%

occurrences of the word "inform" and its variations

No Comments

No Known Activations