INDEX

Explanations

references to tables and data presentations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

getCmp

-0.48

спек

-0.46

 jalan

-0.45

 Parkway

-0.44

PaymentMethod

-0.44

ili

-0.43

oglio

-0.43

createObject

-0.43

限

-0.42

čar

-0.42

POSITIVE LOGITS

 table

1.12

 Table

1.04

 Tables

0.95

 tabel

0.95

 tables

0.94

 tabulated

0.91

 tabular

0.90

TableHead

0.89

Table

0.88

IsContent

0.86

Activations Density 0.450%

references to tables and data presentations in the text

No Comments

No Known Activations