INDEX

Explanations

references to investigations and accusations of fraud or misconduct

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ―――――

-0.82

 itſelf

-0.80

 –,

-0.77

 contextLoads

-0.76

tonode

-0.76

OGND

-0.75

AccessorTable

-0.75

 RSSSF

-0.73

 —,

-0.73

 referenties

-0.73

POSITIVE LOGITS

1.14

1.10

0.81

pic

0.73

 https

0.70

0.69

(@

0.69

0.61

pic

0.60

...@

0.59

Activations Density 0.164%

references to investigations and accusations of fraud or misconduct

No Comments

No Known Activations