INDEX

Explanations

elements related to personal journeys and explorations of growth or progress

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Comté

-0.63

PyExc

-0.57

FunctionFlags

-0.54

//</

-0.52

)_{\

-0.50

icznego

-0.49

forChild

-0.48

 posteriori

-0.48

 catég

-0.48

mahaman

-0.47

POSITIVE LOGITS

 activities

1.24

 happenings

1.18

 activity

1.09

activities

1.04

 things

1.02

 happening

1.01

things

0.98

 doings

0.98

 Activities

0.96

activity

0.96

Activations Density 0.213%

elements related to personal journeys and explorations of growth or progress

No Comments

No Known Activations