INDEX

Explanations

programming-related syntax or keywords

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

böz

-0.71

swick

-0.71

lob

-0.68

ква

-0.67

Cabe

-0.66

ing

-0.65

 Zink

-0.64

 Маль

-0.64

 Swin

-0.62

 Krak

-0.61

POSITIVE LOGITS

:::

1.47

::

1.41

::{

1.27

::

1.21

(::

1.16

>::

1.08

:::

1.04

(&:

0.99

>::

0.96

__::

0.91

Activations Density 0.042%

programming-related syntax or keywords

No Comments

No Known Activations