INDEX

Explanations

occurrences of tables and tabular data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 csin

-0.65

 Gust

-0.65

 ibadah

-0.64

сылкі

-0.62

 doPost

-0.62

Amen

-0.58

 Kokos

-0.58

 Guards

-0.57

Gust

-0.56

 Fuerzas

-0.55

POSITIVE LOGITS

 Table

2.13

Table

2.01

 table

1.84

 TABLE

1.77

 tables

1.75

 Tables

1.72

TABLE

1.71

table

1.50

Tables

1.45

tables

1.37

Activations Density 0.124%

occurrences of tables and tabular data structures

No Comments

No Known Activations