INDEX

Explanations

references to tables and data points in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Dan

-0.40

dom

-0.39

hin

-0.38

vol

-0.36

 caught

-0.35

ônicos

-0.35

-0.34

Dan

-0.34

Dom

-0.34

POSITIVE LOGITS

 table

2.58

 Table

2.18

 tables

2.13

Table

2.10

table

2.06

 TABLE

1.96

TABLE

1.94

 Tables

1.87

 tabular

1.70

 tabel

1.69

Activations Density 0.525%

references to tables and data points in a document

No Comments

No Known Activations