INDEX

Explanations

numerical values, especially in relation to factors or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

@[+][

-0.65

 noDo

-0.56

-0.55

ɒ

-0.54

ře

-0.52

aide

-0.50

-0.49

-0.48

-0.46

on

-0.44

POSITIVE LOGITS

 ExecuteAsync

0.90

 ostavi

0.84

 BoxDecoration

0.82

etheless

0.80

 تضيفلها

0.78

neſs

0.77

theless

0.77

.}~\

0.76

ſtanding

0.74

 समीक्षक

0.74

Activations Density 0.571%

numerical values, especially in relation to factors or classifications

No Comments

No Known Activations