INDEX

Explanations

references to buffer-related terminology in a scientific or technical context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ContentAsync

-0.81

getMinutes

-0.77

DOCTYPE

-0.72

 createSlice

-0.71

featureID

-0.70

AsUp

-0.68

Personensuche

-0.62

 betweenstory

-0.58

IBarButtonItem

-0.58

windowFixed

-0.57

POSITIVE LOGITS

 buffers

0.92

 BUFF

0.83

 Buff

0.82

buffers

0.73

Buffers

0.72

 buffalo

0.70

 Buffer

0.69

 BUFFER

0.69

BUFF

0.69

 buffer

0.69

Activations Density 0.122%

references to buffer-related terminology in a scientific or technical context

No Comments

No Known Activations