INDEX

Explanations

questions related to guidance or instruction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

NameInMap

-0.60

WithIOException

-0.56

#![

-0.55

 архивлан

-0.55

 pinulongan

-0.52

رشف

-0.52

numerusform

-0.50

WithMany

-0.48

jetas

-0.48

Normdaten

-0.47

POSITIVE LOGITS

 NSCoder

0.79

 CreateTagHelper

0.62

 pescoço

0.58

RenderAtEndOf

0.56

 GetEnumerator

0.55

tvguidetime

0.53

RetentionPolicy

0.52

ServletException

0.51

]--;

0.51

 réduite

0.50

Activations Density 0.373%

questions related to guidance or instruction

No Comments

No Known Activations