INDEX

Explanations

checks and comparisons related to identifying the smallest or largest values

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

 EconPapers

-0.78

 initComponents

-0.74

↩

-0.73

expandindo

-0.71

Ibid

-0.68

følgelig

-0.68

 NDEBUG

-0.66

 transfieras

-0.65

näm

-0.65

horabuena

-0.65

POSITIVE LOGITS

 adegu

0.49

 jeweils

0.49

 suitable

0.48

 each

0.48

 corred

0.47

 Indicate

0.47

 appropriate

0.47

 iyong

0.47

 corresponding

0.47

してください

0.44

Activations Density 0.430%

checks and comparisons related to identifying the smallest or largest values

No Comments

No Known Activations