INDEX

Explanations

code structures and data manipulation operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

WriteTagHelper

-0.49

mainAxisSize

-0.49

ational

-0.44

脚注の使い方

-0.43

bil

-0.43

fait

-0.43

 initComponents

-0.42

ナンバー

-0.42

غن

-0.41

ba

-0.41

POSITIVE LOGITS

 reinterpret

0.74

 Pointer

0.72

 itſelf

0.70

ptr

0.67

 myſelf

0.67

 themſelves

0.67

 purpoſe

0.67

 становника

0.66

 address

0.65

 raiſ

0.64

Activations Density 0.188%

code structures and data manipulation operations

No Comments

No Known Activations