INDEX

Explanations

references to place names and geographical locations

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

 '\\;'

-0.59

AccessorTable

-0.53

 OMITBAD

-0.47

XtraReports

-0.47

intios

-0.44

GetAxis

-0.43

➯

-0.43

enumi

-0.43

 Copernicus

-0.42

 ویکی‌پدیای

-0.42

POSITIVE LOGITS

0.83

 league

0.82

 ligand

0.81

 League

0.80

 lieutenant

0.78

le

0.77

LP

0.77

LO

0.77

 Lawrence

0.76

Activations Density 1.502%

references to place names and geographical locations

No Comments

No Known Activations