INDEX

Explanations

references to schemes or methodologies in the text

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

-0.85

 poffible

-0.84

 poffe

-0.77

 ſeveral

-0.75

»»

-0.74

EAT

-0.73

 Overton

-0.73

 myſelf

-0.71

 faſt

-0.71

 Diſ

-0.70

POSITIVE LOGITS

 SCHEME

1.70

Scheme

1.65

 Scheme

1.63

 Schemes

1.61

 scheme

1.61

 schemes

1.59

scheme

1.58

Schemes

1.53

cheme

1.52

SCHEME

1.51

Activations Density 0.057%

references to schemes or methodologies in the text

No Comments

No Known Activations