INDEX

Explanations

references to tables and their attributes in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Ado

-0.56

pch

-0.55

SBATCH

-0.52

outState

-0.50

 userManager

-0.49

 pharmacist

-0.49

canestro

-0.48

 opinion

-0.47

partum

-0.47

 repri

-0.46

POSITIVE LOGITS

table

1.28

 table

1.17

 tables

1.09

tables

1.07

TABLE

1.01

Table

0.95

tagHelperRunner

0.91

 Table

0.90

 Tables

0.90

 TABLE

0.89

Activations Density 0.044%

references to tables and their attributes in the document

No Comments

No Known Activations