INDEX

Explanations

words related to user actions or interactions, particularly those involving tapping or primary actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 iſt

-0.69

 AssemblyVersion

-0.62

igshid

-0.59

 autorytatywna

-0.57

styleType

-0.56

ParallelGroup

-0.56

 CreateTagHelper

-0.54

protoimpl

-0.54

XmlAccessType

-0.53

 ſch

-0.53

POSITIVE LOGITS

 taps

0.59

tap

0.57

 wells

0.56

 Wells

0.52

Keywords

0.50

tap

0.48

 WELLS

0.47

 tapping

0.45

 primary

0.43

keywords

0.43

Activations Density 0.542%

words related to user actions or interactions, particularly those involving tapping or primary actions

No Comments

No Known Activations