INDEX

Explanations

references to time and past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

//

-0.76

CrossRef

-0.70

paramref

-0.59

fillType

-0.59

 propOrder

-0.58

 Freiw

-0.58



-0.58

posedge

-0.57

FieldBuilder

-0.57

зулта

-0.57

POSITIVE LOGITS

 previously

0.99

 previous

0.82

 Previously

0.80

previously

0.78

 past

0.78

Previously

0.74

 PREVIOUS

0.69

 historically

0.67

 anteriormente

0.67

以往

0.66

Activations Density 0.316%

references to time and past events

No Comments

No Known Activations