INDEX

Explanations

code definitions and function declarations in programming contexts

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

 Microb

-0.53

formik

-0.49

Pró

-0.49

rinha

-0.48

 ujednoznacz

-0.47

 shopper

-0.47

 UserController

-0.46

Vegeu

-0.46

 Capture

-0.46

Ѓ

-0.46

POSITIVE LOGITS

 kasarigan

0.67

 Infórmanos

0.58

询问

0.54

 nakalista

0.53

Ans

0.53

发表于

0.53

LCA

0.51

 makl

0.50

 scanf

0.50

enumii

0.50

Activations Density 0.234%

code definitions and function declarations in programming contexts

No Comments

No Known Activations