INDEX

Explanations

expressions of transparency, clarity, and meticulousness in descriptions or statements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-0.67

+#+#

-0.58

IntoConstraints

-0.54

ainville

-0.53

XmlAccessorType

-0.53

niająca

-0.53

çalves

-0.51

sidemargin

-0.51

HomeAsUpEnabled

-0.51

JNIEnv

-0.50

POSITIVE LOGITS

ly

2.42

LY

1.84

lly

1.62

ely

1.55

mente

1.54

ELY

1.45

tly

1.41

ily

1.36

lys

1.36

tely

1.35

Activations Density 0.287%

expressions of transparency, clarity, and meticulousness in descriptions or statements

No Comments

No Known Activations