INDEX

Explanations

words indicating the initiation of actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 autorytatywna

-0.72

RuleContext

-0.59

outWeight

-0.53

исленность

-0.52

tagHelperRunner

-0.52

 typelib

-0.50

 незавершена

-0.48

oredCriteria

-0.48

writeField

-0.47

msgTypes

-0.47

POSITIVE LOGITS

 afresh

0.52

 innocently

0.51

 modestly

0.50

 humbly

0.48

ต้น

0.47

 strong

0.46

 anew

0.46

 promis

0.46

 snippetHide

0.45

 conversations

0.45

Activations Density 0.201%

words indicating the initiation of actions or processes

No Comments

No Known Activations