INDEX

Explanations

conditional phrases indicating choices or alternatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Griffith

-0.81

")));

-0.68

Uli

-0.68

-0.67

 highlights

-0.67

 jsonArray

-0.67

Vivian

-0.66

 ddelweddau

-0.66

enio

-0.66

)++;

-0.65

POSITIVE LOGITS

 Either

1.18

Either

1.12

 either

1.04

ITHER

1.01

either

1.00

ither

0.87

enderror

0.84

weder

0.84

 entweder

0.83

eki

0.77

Activations Density 0.049%

conditional phrases indicating choices or alternatives

No Comments

No Known Activations