INDEX

Explanations

phrases that indicate causation or the means by which something is achieved

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

JoinColumn

-0.60

 Agamemnon

-0.54

andExpect

-0.53

ВД

-0.52

setGeometry

-0.51

WindowConstants

-0.50

сылкі

-0.49

 Mesopotamia

-0.48

imageio

-0.48

onView

-0.48

POSITIVE LOGITS

 InputDecoration

0.69

 createSlice

0.65

__':

0.61

 propOrder

0.61

 sababu

0.61

">.

0.60

AddTagHelper

0.60

PreferredItem

0.53

tiously

0.53

verket

0.52

Activations Density 0.414%

phrases that indicate causation or the means by which something is achieved

No Comments

No Known Activations