INDEX

Explanations

references to permissions, licenses, and disclaimers related to software usage

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

mo

-0.61

 переписи

-0.53

HtmlAttribute

-0.51

pol

-0.46

PerformLayout

-0.45

 originally

-0.44

MO

-0.43

saraba

-0.43

ahn

-0.43

帖最后由

-0.42

POSITIVE LOGITS

jooq

0.69

 betweenstory

0.67

migrationBuilder

0.62

/\.

0.62

thâu

0.59

izr

0.59

ValueGenerated

0.58

UIControlState

0.57

PyExc

0.56

parsedMessage

0.55

Activations Density 0.132%

references to permissions, licenses, and disclaimers related to software usage

No Comments

No Known Activations