INDEX

Explanations

references to specific individuals and places involved in historical or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 تضيفلها

-0.60

esez

-0.59

DMETHOD

-0.54

 cray

-0.53

GRES

-0.52

ropho

-0.51

 Ghat

-0.51

 Plates

-0.50

 instr

-0.50

 fico

-0.48

POSITIVE LOGITS

 barnen

0.61

udin

0.60

uddin

0.58

ullah

0.58

 enfans

0.56

ddin

0.56

GIVEREF

0.55

 AssemblyCulture

0.54

 religieuses

0.54

AndEndTag

0.52

Activations Density 0.121%

references to specific individuals and places involved in historical or political contexts

No Comments

No Known Activations