INDEX

Explanations

references to "polls" and "London."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-1.08

 myſelf

-0.88

 Monfieur

-0.88

 Majefty

-0.87

Eſ

-0.86

 pleaſure

-0.85

 Theſe

-0.85

 ſeveral

-0.83

ſy

-0.82

 ſtate

-0.81

POSITIVE LOGITS

Abitanti

0.60

0.58

 Table

0.57

 cherchés

0.57

veloped

0.54

0.53

 London

0.51

au

0.50

amship

0.48

Activations Density 0.193%

references to "polls" and "London."

No Comments

No Known Activations