INDEX

Explanations

references to the use of specific techniques or methods in various contexts

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

 output

-0.51

mo

-0.51

 суда

-0.50

co

-0.49

esity

-0.48

di

-0.48

ben

-0.47

 punya

-0.47

ERTY

-0.47

войства

-0.46

POSITIVE LOGITS

 uſed

1.02

 used

0.97

 pleaſure

0.88

 raiſ

0.88

parsedMessage

0.86

 متعلقه

0.86

Efq

0.84

#![

0.83

 ſta

0.83

 Anſ

0.81

Activations Density 0.176%

references to the use of specific techniques or methods in various contexts

No Comments

No Known Activations