INDEX

Explanations

conditional statements and possibilities in reasoning or argumentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

addCriterion

-0.75

MessageOf

-0.72

 <>",

-0.68

ніципа

-0.65

GEBURTS

-0.64

 bershka

-0.63

ⓧ

-0.62

 >=",

-0.62

ourite

-0.62

Efq

-0.61

POSITIVE LOGITS

 only

0.61

要么

0.59

除非

0.57

 either

0.56

 Either

0.53

 unless

0.52

 Only

0.51

Only

0.50

要不

0.49

to

0.47

Activations Density 0.354%

conditional statements and possibilities in reasoning or argumentation

No Comments

No Known Activations