INDEX

Explanations

references to vehicle makes and models, particularly related to accidents or incidents involving them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ьаж

-0.73

 Paglinawan

-0.69

المكان

-0.62

 nahilalakip

-0.59

 BorderSide

-0.59



-0.58

Портал

-0.58

ChildIndex

-0.58

addGap

-0.57

addPreferredGap

-0.56

POSITIVE LOGITS

RenderAtEndOf

0.60

#+#

0.57

IndentedString

0.47

 rastre

0.46

 Eing

0.46

sph

0.45

 kasarigan

0.44

 antique

0.44

 spor

0.43

مي

0.42

Activations Density 0.381%

references to vehicle makes and models, particularly related to accidents or incidents involving them

No Comments

No Known Activations