INDEX

Explanations

syntactic structures related to code snippets or programming language syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

RTDA

-0.81

 protoimpl

-0.76

 estekak

-0.75

 Chwiliwch

-0.71

ImageContext

-0.70

ValueStyle

-0.70

 <<<<<<<<<<<<<<

-0.69

Rüyada

-0.69

principalColumn

-0.68

MENAFN

-0.67

POSITIVE LOGITS

AutoScale

0.48

ôm

0.44

acer

0.43

WebControls

0.43

 nocturn

0.42

Facing

0.41

 Verhältnisse

0.41

 Gibson

0.40

consistency

0.39

Backend

0.39

Activations Density 0.035%

syntactic structures related to code snippets or programming language syntax

No Comments

No Known Activations