INDEX

Explanations

section dividers or headings 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.70

RetentionPolicy

-0.64

-0.63

ch

-0.63

-0.62

द

-0.58

-0.57

ab

-0.57

sub

-0.57

-0.56

POSITIVE LOGITS

==========

1.19

 ------

1.17

 ----------

1.15

----------

1.15

===========

1.14

============

1.14

=============

1.13

 --------

1.11

 -----------

1.11

=========

1.11

Activations Density 0.231%

section dividers or headings in the document

No Comments

No Known Activations