INDEX

Explanations

references to events involving political actions and 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

fillType

-0.64

 unknownFields

-0.51

 prenn

-0.50

emoc

-0.50

 Happened

-0.49

écial

-0.49

 meub

-0.48

acier

-0.48

StoreMessageInfo

-0.47

assertThat

-0.47

POSITIVE LOGITS

 sent

0.66

 raised

0.65

 killed

0.63

 executed

0.61

 deported

0.61

 thrown

0.61

 marty

0.61

lyn

0.59

 hanged

0.58

 assassinated

0.57

Activations Density 0.458%

references to events involving political actions and consequences

No Comments

No Known Activations

references to events involving political actions and consequences

No Comments

No Known Activations