INDEX

Explanations

instances of press conferences and discussions surrounding notable events or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 المعيارى

-0.84

 Anſ

-0.81

 pleaſure

-0.75

 Chrift

-0.74

حياتها

-0.74

 transfieras

-0.74

Eſ

-0.73

 raiſ

-0.73

 Houſe

-0.73

 purpoſe

-0.71

POSITIVE LOGITS

BeginContext

0.68

 Douglas

0.65

ach

0.60

Douglas

0.57

 Lego

0.56

Fab

0.54

 Graham

0.54

帖最后由

0.54

Lego

0.51

Naissance

0.50

Activations Density 0.940%

instances of press conferences and discussions surrounding notable events or figures

No Comments

No Known Activations