INDEX

Explanations

terms related to results and their documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ialmente

-0.57

rinfo

-0.51

miss

-0.50

viously

-0.48

 baile

-0.48

ibb

-0.47

اطر

-0.47

errorMessage

-0.44

 miss

-0.43

 hechas

-0.43

POSITIVE LOGITS

स्व

0.78

 Infórmanos

0.72

 propOrder

0.70

물

0.68

mphony

0.68

 getResult

0.68

 therefrom

0.67

 results

0.66

 Results

0.65

Quo

0.65

Activations Density 0.197%

terms related to results and their documentation

No Comments

No Known Activations