INDEX

Explanations

references to readers and their understanding or acknowledgment of content

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

addContainerGap

-0.61

يكب

-0.59

uzen

-0.58

JsonHelper

-0.57

WithIOException

-0.56

 SwitchCompat

-0.56

InstrumentedTest

-0.53

 wherefore

-0.53

 combineReducers

-0.51

moveToFirst

-0.51

POSITIVE LOGITS

 probably

1.42

Probably

1.26

 familiar

1.24

 Probably

1.23

probably

1.23

familiar

1.16

Familiar

1.08

 Familiar

1.02

 doubtless

1.02

 probablemente

0.95

Activations Density 0.251%

references to readers and their understanding or acknowledgment of content

No Comments

No Known Activations