INDEX

Explanations

references to other individuals or entities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Efq

-0.72

 himſelf

-0.63

ündig

-0.59

 ulcers

-0.58

 Grot

-0.57

colorPrimary

-0.57

 Progres

-0.56

andExpect

-0.55

 Theſe

-0.54

<_>

-0.54

POSITIVE LOGITS

 than

0.61

 himo

0.60

 outros

0.59

principalTable

0.58

 elsewhere

0.58

Outras

0.58

########.

0.57

Elsewhere

0.57

Others

0.57

 other

0.57

Activations Density 0.507%

references to other individuals or entities in various contexts

No Comments

No Known Activations