INDEX

Explanations

references to government, authority, or legal responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

bereits

-0.60

значно

-0.60

 poveznice

-0.59

 hooves

-0.58

conuts

-0.58

 dreamstime

-0.58

liosis

-0.57

 proactively

-0.55

 beft

-0.54

 Autres

-0.54

POSITIVE LOGITS

ValueStyle

0.60

Biographie

0.57

WriteBarrier

0.57

 通販

0.56

FontStyle

0.55

featureID

0.53

wb

0.52

 difficulty

0.51

ustom

0.50

mány

0.50

Activations Density 1.336%

references to government, authority, or legal responsibilities

No Comments

No Known Activations