INDEX

Explanations

references to people or entities involved 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

Rüyada

-0.50

 annual

-0.48

fo

-0.46

 anniversary

-0.46

mpä

-0.46

’

-0.44

ata

-0.43

one

-0.43

DF

-0.43

POSITIVE LOGITS

PerformLayout

1.19

WriteTagHelper

1.01

findpost

0.97

ⓧ

0.91

 CreateTagHelper

0.89

rungsseite

0.88

 pylint

0.86

verwijspagina

0.83

ValueStyle

0.82

PreExecute

0.79

Activations Density 0.295%

references to people or entities involved in various contexts

No Comments

No Known Activations