INDEX

Explanations

references to scientific authors and their published works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Datuak

-0.96

{#

-0.75

setVerticalGroup

-0.73

 Exact

-0.72

createStatement

-0.71

PRNewswire

-0.69

/*---

-0.68

 &___

-0.66

 XCTest

-0.65

팎

-0.64

POSITIVE LOGITS

 Lohan

1.02

LS

0.93

Ls

0.93

0.91

LF

0.85

LCS

0.84

Ll

0.84

esgue

0.81

 Lyons

0.80

LU

0.79

Activations Density 1.041%

references to scientific authors and their published works

No Comments

No Known Activations