INDEX

Explanations

actions related to attempts to communicate or escape situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

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

 AssemblyProduct

-0.69

 архивлан

-0.67

--)

-0.64

 insuffisamment

-0.64

ArgsConstructor

-0.63

.",

-0.61

`,

-0.59

"](

-0.58

argout

-0.56

routeProvider

-0.56

POSITIVE LOGITS

 attempts

0.52

try

0.50

 versucht

0.48

try

0.48

KEYCODE

0.48

فسير

0.48

 пыта

0.47

 trying

0.46

试图

0.46

äiv

0.46

Activations Density 0.250%

actions related to attempts to communicate or escape situations

No Comments

No Known Activations