INDEX

Explanations

references to prior studies or previous research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

artamento

-0.65

 QtGui

-0.59

 getStart

-0.57

 wachs

-0.55

 पूरा

-0.55

 fær

-0.55

 completas

-0.54

raszamy

-0.52

 başlay

-0.52

 segera

-0.52

POSITIVE LOGITS

StoryboardSegue

0.90

 Previous

0.83

PREVIOUS

0.82

Previous

0.80

itisation

0.80

ädie

0.79

 виправивши

0.77

previous

0.74

 previous

0.74

__':

0.74

Activations Density 0.128%

references to prior studies or previous research

No Comments

No Known Activations