INDEX

Explanations

references to original hypotheses or claims in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 विश्वसनीयता

-0.53

انجليز

-0.47

addPreferredGap

-0.47

ourable

-0.47

 meglio

-0.46

 transition

-0.45

 آخرین

-0.43

 Transition

-0.43

enumi

-0.41

transition

-0.41

POSITIVE LOGITS

 originals

0.85

InvalidProtocol

0.80

 Wikimedijinoj

0.74

 originales

0.73

 originais

0.71

principalTable

0.71

 original

0.69

ruptedException

0.69

 orig

0.65

 AssemblyCulture

0.65

Activations Density 0.622%

references to original hypotheses or claims in a scientific context

No Comments

No Known Activations