INDEX

Explanations

information related to software updates and error messages

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

citations and references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 otomatig

-0.72

 kaarangay

-0.61

 Photocase

-0.60

tonode

-0.59

 gyhoeddwyd

-0.59

 الحره

-0.58

 <>",

-0.57

AnchorTagHelper

-0.57

 nonUne

-0.56

رشف

-0.56

POSITIVE LOGITS

Kaynakça

0.50

 lemp

0.36

각주

0.35

 faça

0.34

 fique

0.33

Референце

0.33

Наводи

0.33

ographia

0.33

0.31

 systematic

0.31

Activations Density 0.022%

information related to software updates and error messages

citations and references

No Comments

No Known Activations