INDEX

Explanations

phrases indicating prior actions or events leading to current states or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 يتيمه

-0.60

pired

-0.60

(!__

-0.57

AndroidJUnit

-0.57

tagHelper

-0.56

ejs

-0.52

__":

-0.51

Personensuche

-0.50

GraphicsUnit

-0.49

 berlaku

-0.49

POSITIVE LOGITS

 move

1.82

 transition

1.65

 moved

1.61

move

1.59

 Move

1.56

 moves

1.51

 transitioned

1.48

 moving

1.46

 transitioning

1.45

Move

1.42

Activations Density 0.501%

phrases indicating prior actions or events leading to current states or consequences

No Comments

No Known Activations