INDEX

Explanations

sections of text related to events and outcomes

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

dafx

-0.61

OGND

-0.56

Jegyzetek

-0.55

ItemBackground

-0.54

ệc

-0.54

Hauptartikel

-0.52

rawtypes

-0.52

دانشنامهٔ

-0.52

)]$

-0.52

principalTable

-0.51

POSITIVE LOGITS

 wonderful

2.33

 amazing

2.08

 lovely

2.04

wonderful

2.00

 beautiful

1.99

 marvellous

1.96

 marvelous

1.96

 magnificent

1.87

 fabulous

1.85

 delightful

1.85

Activations Density 0.252%

sections of text related to events and outcomes

No Comments

No Known Activations