INDEX

Explanations

terms related to reducing size or quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

enumi

-0.92

enderror

-0.90

QMetaType

-0.82

 Dundas

-0.79

Hozzáférés

-0.79

vVar

-0.79

tableFuture

-0.77

istocene

-0.77

baomidou

-0.77

شهاد

-0.76

POSITIVE LOGITS

Shr

1.29

Shr

1.27

 shrink

1.23

 Shrink

1.20

shrink

1.17

SHR

1.13

shr

1.13

Shrink

1.03

 shrinkage

1.02

 shrinking

0.98

Activations Density 0.026%

terms related to reducing size or quantity

No Comments

No Known Activations