INDEX

Explanations

punctuation marks and their associated contexts

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

ConstraintMaker

-1.03

 يتيمه

-0.88

 للاسماء

-0.84

 Chwiliwch

-0.77

andExpect

-0.75

DockStyle

-0.75

/\.

-0.73

Rhestr

-0.71

 فريبيس

-0.69

ècie

-0.69

POSITIVE LOGITS

 ramai

0.52

 podpor

0.51

 sexuales

0.50

 pensée

0.47

 noqa

0.47

 SwitchCompat

0.47

 dieną

0.45

性に

0.44

 cuchar

0.44

孽

0.43

Activations Density 0.247%

punctuation marks and their associated contexts

No Comments

No Known Activations