INDEX

Explanations

references to authority and religious texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 sérieux

-0.56

 labios

-0.50

nanoTime

-0.49

 littéraire

-0.48

antwoorden

-0.48

 conmigo

-0.47

 уха

-0.47

 alvor

-0.47

 utafitiHapana

-0.47

 chré

-0.47

POSITIVE LOGITS

 محفوظة

0.86

ukone

0.84

 Савезне

0.82

 كومونز

0.80

 Мексичка

0.79

 مُعرِّف

0.74

PhysRev

0.72

AutoScaleMode

0.72

 CreateTagHelper

0.71

 "..\..\

0.70

Activations Density 0.270%

references to authority and religious texts

No Comments

No Known Activations