INDEX

Explanations

expressions related to fixing or resolving issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

styleType

-0.79

 demografica

-0.63

 незавершена

-0.61

 Braut

-0.55

āci

-0.54

undang

-0.54

 hjemme

-0.54

 csoport

-0.53

[],

-0.53

 vanskelig

-0.53

POSITIVE LOGITS

fix

4.46

Fix

4.14

fix

4.09

Fix

3.93

FIX

3.47

 fixing

3.28

 fixes

3.26

FIX

3.18

 Fixing

3.06

fixing

2.92

Activations Density 0.061%

expressions related to fixing or resolving issues

No Comments

No Known Activations