INDEX

Explanations

references to sharing concepts or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

WithIOException

-0.56

MENAFN

-0.55

Manbalar

-0.54

IndentedString

-0.54

:✨

-0.53

 lenker

-0.52

jspx

-0.51

VIAF

-0.51

enumii

-0.51

 BufferedReader

-0.49

POSITIVE LOGITS

 share

4.01

 sharing

3.88

 shared

3.71

share

3.68

 Share

3.57

 Sharing

3.51

Share

3.46

sharing

3.41

Sharing

3.40

 shares

3.37

Activations Density 0.467%

references to sharing concepts or items

No Comments

No Known Activations