INDEX

Explanations

references to tables within 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 doInBackground

-0.75

 Kokos

-0.67

quiere

-0.64

σιμοποι

-0.64

skraft

-0.64

 Eros

-0.63

Virgo

-0.61

 revient

-0.61

]))

-0.60

OrNil

-0.60

POSITIVE LOGITS

 tables

1.80

 table

1.78

 Table

1.71

 Tables

1.62

 TABLE

1.50

Table

1.49

table

1.41

 tabled

1.30

Tables

1.28

tables

1.28

Activations Density 0.099%

references to tables within the text

No Comments

No Known Activations