INDEX

Explanations

repeated mentions of "of" in various contexts, indicating specificity and relationships within complex descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

sendStatus

-0.46

urre

-0.43

 Miss

-0.41

mathrm

-0.40

顧

-0.39

胎

-0.39

晚

-0.38

Pageable

-0.37

ěst

-0.36

 candid

-0.36

POSITIVE LOGITS

<bos>

0.97

PyExc

0.90

 MonoBehaviour

0.85

aarrggbb

0.80

AddHtmlAttribute

0.78

Datuak

0.76

WebVitals

0.76

 AssemblyCompany

0.76

setVerticalGroup

0.74

 ModelExpression

0.73

Activations Density 1.086%

repeated mentions of "of" in various contexts, indicating specificity and relationships within complex descriptions

No Comments

No Known Activations