INDEX

Explanations

text related to scientific studies and research.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

specific names or terms of significant importance in a particular context.

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

names or words starting with "Shi", particularly in scientific or academic contexts.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

starting with "Shi" or "Shi-"

np_acts-logits-general · gemini-2.0-flash

words starting with Shi

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

ANNES

-0.68

tagHelperRunner

-0.65

⋙

-0.65

vieren

-0.64

ReusableCell

-0.62

Gambas

-0.62

談社

-0.58

Lưu

-0.56

BrowserModule

-0.55

bangunan

-0.55

POSITIVE LOGITS

Shi

0.86

Shi

0.81

shi

0.77

 OnInit

0.66

 Schi

0.61

shi

0.60

Shir

0.59

shiro

0.54

 Happens

0.53

 shifter

0.52

Activations Density 0.064%